Bibliography

1 ADORNO, Theodor W. , et al. , The authoritarian personality, New York, Harper, 1950.

2 ALLARDT, Erik , `The merger of American and European traditions of sociological research: contextual analysis', Social Science Information, 7, 1968: 151-168. In an historical context the aim of contextual research is outlined: the integration of a collectivistic and an individualistic approach to society.

3 ALLARDT, Erik , `Aggregate analysis: the problem of its informative value' in: Mattei L. Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 41-51. The informative value of multi-level propositions is high because of the attempt to connect phenomena on differing social levels.

4 ALLARDT, Erik , `Evolutionary, structural and institutional characteristics of societies', Acta Sociologica, 12, 1969: 74-84. Four major strategies are treated that are relevant for the development of models of `comparative study of the structure and development of national societies'.

5 ALLARDT, Erik , `Structural, institutional and cultural explanation', Acta Sociologica, 15, 1972: 54-68. In this article a new typology of modes of explanation is developed by `cross-tabulating' two kinds of classifications.

6 BARTON, Allen H. , `Bringing society back in survey research and macro-methodology', The American Behavioral Scientist, 12, 1968: 1-9. A plea for quantitative research methods by which both individual variables and social context can be analyzed.

7 BAUMGARTNER, Thomas , BURNS, Tom R. , MEEKER, L. David , WILD, Bradford , `Open systems and multi-level processes: implications for social research', Quality and Quantity, 11, 1977: 287-328. A preliminary development of a research procedure helpful in the detection and differentiation of multi-level processes.

8 BECKMAN, Dieter , `Die Abhängigkeit des Einzelne von Gruppenprozessen' (The dependence of a group member upon group processes), Gruppendynamik, 3, 1972: 62-79. An investigation of the relationship between certain structural characteristics of a `closed shop', and typical interaction patterns of the group members.

9 BERRY, K.J. , MARTIN, Th. W. , `The synecdochic fallacy: a challenge to recent research and theory building in sociology', Pacific Sociological Review, 17, 1974: 139-166. On the basis of theoretical considerations the conclusion is drawn that `there is always the danger of committing a fallacy of reasoning when the unit to which an inference refers is smaller or larger than the unit of observation, no matter the direction in which the inference is drawn'.

10 BLALOCK, Hubert M., jun. , Theory construction: from verbal to mathematical formulations, Englewood Cliffs, NJ, Prentice-Hall, 1969. Chapter 7, titled `Generalizations and Levels of Abstractions' indicates, among other things, the relationship between different levels.

11 BLALOCK, Hubert M., jun. , `The presidential address: measurement and conceptualization problems: the major obstacle to integrating theory and research', American Sociological Review, 44, 1979: 881-894. The necessity to carry out theoretical and methodological analysis at the same time is illustrated with the problem of theoretical definitions of generic behaviour and their implications for measurement, and the confounding of measured and unmeasured variables when individuals are aggregated in macro-level analysis.

12 BLALOCK, Hubert M., jun. , WILKEN, Paul H. , Intergroup processes: a micro-macro perspective, New York, Free Press/London, Collier Macmillan, 1979. This volume contains a chapter (pp. 288-324) offering a clear overview of issues in contextual-effects research.

13 BLAU, Peter M. , `Structural effects', American Sociological Review, 25, 1960: 178-193. This paper argues that the impact of social values on individual behaviour is twofold: one part is outside the individual, the other belongs to the individual himself.

14 BLAU, Peter M. , `Parameters of social structure', American Sociological Review, 39, 1974: 615-635. A typology of parameters that characterize social structure, such as `nominal parameters which divide people into subgroups and engender heterogeneity, and graduated parameters which differentiate people in terms of status rankings and engender inequality'.

15 CAMPBELL, Ernest Q. , ALEXANDER, C. Norman , `Structural effects and interpersonal relationships', American Journal of Sociology, 71, 1965: 284-290. `It is proposed that structural effects be analyzed with a two-step model that employs structural variables to predict the relevant characteristics of an individual's social environment and then explains his behaviors in terms of a social psychological theory whose prediction takes these conditions of the social environment as given.'

16 COHEN, Jere M. , `Sources of peer group homogeneity', Sociology of Education, 50, 1977: 227-241. On the basis of the results of research into factors that increase `homogeneity in student friendship groups, the conclusion is drawn that the magnitude of peer influence on aspirations has been overestimated in the status-attainment literature'.

17 COLEMAN, James S. , `Comment on three “climate of opinion” studies', Public Opinion Quarterly, 25, 1961: 607-610. An evaluation of three studies in a special issue of Public Opinion Quarterly (see 61).

(Reprinted in: Joseph Berger , Morris Zelditch, jun. , and Bo Andersen (eds), Sociological theories in progress, Boston, Houghton Mifflin, 1971-72: 74-101.) `Balance theory, a theoretical system developed by Cartwright and Harary to formalize concepts set forth by Heider, is used with slight modifications to restate fifty-six sociological and social-psychological propositions.'

19 DAVIS, James A. , `The campus as a frog-pond: an application of the theory of relative deprivation to career decisions of college men', American Journal of Sociology, 72, 1966: 17-31. In this investigation it is demonstrated that the belief of students in their own success, based on comparison of their own study achievements with those of other students at the same colleges, influences the ambition to reach higher social positions. The quality of the colleges appears not to have any impact. The explanatory value of study achievements is strengthened by feelings of success with respect to a given study.

(Enlarged version in: Mattei Dogan and Stein Rokkan (eds), Quantitative, ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969.) An introduction to problems of quantitative multi-level research.

21 EBERLEIN, Gerald , Theoretische Soziologie Heute. Von allgemeinen Sozialtheorien zum soziologischen Kontextualmodell (Theoretical sociology today: from general social theories to sociological contextual model), Stuttgart, Ferdinand Enke Verlag, 1971. A theoretical legitimation of the contextual research model is offered by indicating the sociological relevance of the concept of context.

22 EDEL, Abel , `The concept of levels in social theory' in: Lewelyn Gross (ed.), Symposium on sociological theory, White Plains, NY, 1959: 167-196. A critique of the traditional concept of `emergent levels' and a plan for scientific application of a more liberalized concept.

23 EEDEN, Pieter van den , `Niveau's van analyse in sociaal onderzoek' (Levels of analysis in social research), Geografisch Tijdschrift, Nieuwe Reeks, 12, 1978: 27-33. A definition of the concept of `social level' is offered: each of the poles of an inclusion relationship that orders a pair of units. A description of current multi-level research is added.

24 EIRMBTER, Willy H. , `Zur Theorie und Methodik von Mehrebenenanalyse' (Theory and methodology from multi-level analysis), Kölner Zeitschrift für Soziologie und Sozial-Psychologie, 4, 1979: 709-731. A multi-level programme is presented as an opportunity to solve the discrepancy between theory development and empirical research.

(Reprinted in: Edgar F. Borgatta and David J. Jackson (eds), Aggregate data: analysis and interpretation, Beverly Hills/London, Sage Publications, 1980: 25-59, `Treatments of contextual effects in the social science literature have traditionally focused on statistical phenomena more than on social processes. Typically, the existence of contextual processes has been inferred on the basis of “group-level” effects (as contrasted with “individual-level” effects).' This article seeks to redress that imbalance by focusing on underlying processes through which social structure and social interaction may impinge upon individuals.

26 EULAU, Heinz , `On units and levels of analysis' in: Heinz Eulau, Micro-macro political analysis: accents of inquiry, Chicago, Aldine, 1969: 1-19. An introduction into the problem of shift of levels with respect to individual behaviour within groups.

27 EULAU, Heinz , `Multi-level methods in comparative politics', American Behavioral Scientist, 21, 1977: 39-61. This paper reviews some of the intellectual and theoretical issues that are germane to data transformation from one level to another level of analysis.

28 FALTER, Jürgen, W. , `Some theoretical and methodological problems of multi-level analysis reconsidered', Social Science Information, 17, 1978: 841-869. A general introduction to several important aspects of the multi-level design.

29 FIREBAUGH, Glen , `Groups as contexts and frog ponds: some neglected considerations' in: Karlene H. Roberts and Leigh Burstein (eds), Issues in aggregation, San Francisco, Jossey Bass Inc., 1980: 43-52. The concept of context is explored, and comparisons between different contextual effects are discussed.

30 FRIDERES, James S. , WARNER, Lyle G. , ALBRECHT, Stan L. , `The impact of social constraints on the relationship between attitudes and behavior', Social Forces, 50, 1971: 102-112. `This research tries to assess the effects of social participation, attitudinal congruence and disclosure on the relationship between a subject's attitude toward legalizing marijuana and an overt act toward that same attitude object.'

31 FRIEDRICHS, Jürgen , `Situation als soziologische Erhebungseinheit' (The situation as a sociological unit of analysis), Zeitschrift für Soziologie, 3, 1973: 44-53. `The question is asked whether the concept of situation can be meaningfully employed as a unit of observation in sociological investigations. Based on a proposed definition, some examples from actual research are presented to illustrate in what ways the structural characteristic “situation” can be used.'

32 GALTUNG, Johan , Theory and methods of social research, Oslo, Universitetsforlaget, Part I, 1967: 1-108. This textbook extensively treats the distinctions between kinds of units and their attributable characteristics.

33 GILLI, Gian Antonio , `Effetti Strutturali' (Structural effects), Quaderni di Soziologia, 14, 1965: 171-199. A general outline and a critique of the literature on structural-effect analysis.

34 HAMBLIN, Robert L. , JACOBSEN, R. Brooke , MILLER, Jerry L. , A mathematical theory of social change, New York, NY, Wiley, 1973.

35 HIRSCH, Travis , SELVIN, Hanan C. , Delinquency research, Free Press, New York, 1967. (Reprinted as: Principles of survey analysis, Free Press, New York, 1973.) In this textbook on survey research, much attention is paid to the basic concepts of the multi-level approach.

36 HUMMELL. Hans-Joachim , Probleme der Mehrebenenanalyse (Problems of Multi-level research), Stuttgart, Teubner, 1972. The first systematic outline of issues in multi-level theory and research.

37 HUMMELL, Hans-Joachim , OPP, Karl-Dieter , Die Reduzierbarkeit von Soziologie auf Psychologie (The reduction of sociology to psychology), Braunschweig Vieweg, 1971. Propositions that appear to be sociological par excellence are `unmasked' as psychological propositions.

38 KAPPELHOFF, Peter , `Zur Strukturanalyse von primären Umwelten' (Towards a structural analysis of primary environments), Zeitschrift für Soziologie, 8, 1979: 145-157. The author recommends that empirically assessed data be expressed in a mathematical symbol language. The analysis consists of the distinction of rational structures in `zones of relative densification', on which a network analysis by means of statistical methods can be carried out.

39 KATZ, Elihu , HAMILTON, Herbert , LEVIN, Martin L. , `Traditions of research on the diffusion of innovation', American Sociological Review, 8, 1963: 237ff. `The process of diffusion is defined as the (1) acceptance, (2) over time, (3) of some specific item — an idea or practice, (4) by individuals, groups or other adopting units, linked to (5) specific channels of communication, (6) to a social structure, and (7) to a given system of values, or culture.'

40 KENDALL, Patricia , LAZARSFELD, Paul F. , `Problems of survey analysis' in: Robert K. Merton and Paul F. Lazarsfeld (eds), Studies in the scope and method of `the American soldier', Glencoe, Ill., Free Press, 1950: 163-196. This is an article about the possibilities of indicating contextual properties via individual data.

41 LAZARSFELD, Paul F. , `Problems in methodology' in: Robert K. Merton , Leo Broom and L.S. Cottrell (eds), Sociology today, New York, Basic Books, 1959: 39-78. An introduction to several methodological issues, such as `contextual propositions' and their central locations in social science methodology.

42 LAZARSFELD, Paul F. , MENZEL Herbert , `On the relation between individual and collective properties' in: Amitai Etzioni (ed.), Complex organizations, New York, Holt, Rinehart and Winston, 1961: 422-440. A classical article on multi-level research in which kinds of group and individual characteristics are formally distinguished.

43 LEEUW, Antonius C.J., de , Systeemleer en organisatiekunde (System and organization theory), Leiden, Stenfert Kroese, 1974: 91-113. An attempt to develop a system theory which pays attention to the relationship between different levels.

44 LEEUW, Antonius C.J., de , Hiërarchische systemen (Hierarchical systems), Eindhoven, Technological University, 1976. A theoretical outline of the meaning of the term `hierarchical systems'.

45 LINDENBERG, Siegwart , `Individuelle Effekte, Kollektive Phänomene und das Problem der Transformation' (Individual effects, collective phenomena and the transformation problem), in: Klaus Eichner and Werner Habermehl (eds), Probleme der Erklärung Sozialen Verhaltens (Problems of explanation of social behaviour), Meisenheim am Glau, Verlag Anton Hain, 1977: 46-84. An ethological approach to the problem of connecting different social levels. The translation of phenomena of one level into phenomena of another level has been called `transformation'.

46 MAYHEW, Bruce H. , LEVINGER, Roger L. , `Size and the density of interaction of human aggregates', American Journal of Sociology, 82, 1976: 86-110. `A baseline model is developed to show the conductiveness of population size to the density of interaction in human aggregates. This model permits deduction and, therefore, explanation of a wide variety of social phenomena.'

47 MERTON, Robert K. , Social theory and social structure, New York, Free Press, 1968. [Revised edition.]

48 NIGSCH, Otto , `Theoretische und praktische Bedeutung der Mehrebenenanalyse' (Theoretical and practical significance of multi-level analysis), Kölner Zeitschrift für Soziologie und Sozialpsychologie, 29, 1977: 561-576. An article about theoretical presuppositions of the multi-level research model.

49 NOWOTNY, Helga , `Selbst mehrere Ebenen ergeben noch keine Struktur: ein Beitrag zur Mehrebenenanalyse' (Even multiple levels do not yield any structure: a contribution to multi-level analysis), in: A. Holl , and O.W. Saipt (eds), Oesterreichisches Jahrbuch für Soziologie, Wien/Köln, Grasz, 1974. A critical discussion of the restrictions that sociologists apply in their analysis.

50 OPP, Karl-Dieter , `Group size, emergence, and composition bias: are there macroscopic theories sui generis?' Philosophy of Social Sciences, 9, 1979: 445-455. Composition laws are not always connected with individual theories.

51 PITT-RIVERS, Julian , `Contextual analysis and the locus of the model', Archives Européennes de Sociologie, 8, 1967: 15-34. A plea for an integrated analysis of micro-and macro-aspects of society.

52 PRZEWORSKI, Adam , TEUNE, Henri , The logic of comparative social inquiry, New York, Wiley, 1970. Some simple designs based on the number of levels of analysis and the nature of the dependent variable are discussed.

53 RILEY, Mathilda White , `Special problems of sociological analysis' in: Mathilda White Riley, Sociological research I: a case approach, New York, Harcourt, Brace, Jovanovich 1963: 700-739. This chapter discusses the multi-level paradigm on the basis of research illustrations.

54 RILEY, Mathilda W. , `Sources and types of sociological data' in: Robert E.L. Faris, Handbook of modern sociology, Chicago, Rand McNally, 1964: 978-1023. By means of a general model of social research, various phases of the research process are investigated in terms of the degree to which methods suit particular data. Special attention is paid to multi-level analysis procedures.

55 ROKKAN, Stein , `Cross-national research: historical, analytical, and substantive contexts' in: Stein Rokkan , Sidney Verba , Jean Viet and Elina Almasy (eds), Comparative survey analysis, Paris/The Hague, Mouton, 1969: 5-55. The historical, analytical and substantive contexts of cross-national research are treated.

56 ROSENBERG, Morris , The logic of survey analysis, New York/London, Basic Books, 1968. In this monograph attention is paid to the unit of analysis issue. At least seven levels of sociological analysis are distinguished.

57 SELVIN, Hanan, C. , `Durkheim's Suicide and problems of empirical research', American Journal of Sociology, 63, 1958: 607-619. The methodological starting points in Durkheim's Suicide are analyzed.

58 SELVIN, Hanan C. , HAGSTROM, Warren O. , `The empirical classification of formal groups', American Sociological Review, 28, 1963: 399-411. By means of the application of factor analysis on aggregate group characteristics a number of factors are deduced, to be interpreted as the main formal group characteristics.

[See James A. Davis , `Group variables', American Sociological Review, 28, 1963: 814.]

60 SHIVELY, W. Phillips , `Utilizing external evidence in crosslevel inference', Political Methodology, 1, 1974: 61-72. In this article a technique is presented for ecological inference which does not involve ecological regression.

61 SILLS, David L. , `Three “climate of opinion” studies', Public Opinion Quarterly, 25, 1961: 571-573. `Opinion is surely not formed in social vacuum; it cannot be understood without an understanding of its relations to its environment' (see 17).

62 SIMON, Herbert A. , GUETZKOW, Harold H. , `Mechanisms involved in pressures toward uniformity in groups' in: Paul F. Lazarsfeld and Neil W. Henry (eds), Readings in mathematical social sciences, Cambridge, Mass./London, MIT Press, 1966. This paper brings forward the synthesis of propositions of Festinger into an interrelated system, differentiating short-run mechanisms from those involved in the long run.

63 SINGER, J. David , `The level-of-analysis problem in political relations', World Politics, 14, 1961: 77-92. `The purpose of this paper is to raise the issue of levels of analysis, articulate the alternatives, and examine the theoretical implications and consequences of two of the more widely employed levels of analysis, the international system and the national sub-system.'

64 SØRENSEN, Aage B. , `Reconceptualizing school effects (a reply to Hauser)', Sociology of Education, 51, 1978: 230-233. A reaction to Hauser's comments on an article by Sørensen and Hallinan (see 218).

65 STINCHCOMBE, Arthur L. , Constructing social theories, New York, Harcourt, Brace and World, 1968. Chapter V, entitled `The Conceptualization of Environmental Effects', presents several types of explanation of multi-level effects. The emphasis is on (a) an individual's identification with his group, (b) the opportunities offered by a collectivity to an individual, (c) his aspiration, and (d) his tendency to lower his vulnerability.

66 STOUFFER, S.A. , Studies in social psychology in world war II, Vol. I, The American soldier during army life, Princeton, NJ, Princeton University Press, 1949.

67 TAYLOR, Howard , HORNUNG, Carlton A. , `On a general model for social and cognitive consistency', Sociological Methods and Research, 7, 1979: 259-287. `Several important studies of cognitive consistency theory are reviewed to locate conceptual omissions in tests of the theory. Several issues that are problematic in testing consistency theory are reviewed, alternative solutions are discussed and areas in which additional work is needed are noted.'

68 VALKONEN, Tapai , `Individual and structural effects in ecological research' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 53-68. An attempt to consider ecological research as multi-level research.

69 VERBA, Sidney , `The uses of survey research in the study of comparative politics: issues and strategies' in: Stein Rokkan , Sidney Verba , Jean Viet and Elina Almasy (eds), Comparative survey analysis, Paris/The Hague, Mouton, 1969: 56-106. Verba distinguishes three approaches in the application of a comparative survey research design.

70 WAGNER, Helmut R. , `Displacement of scope: a problem of the relationship between small-scale and large-scale sociological theories', American Journal of Sociology, 69, 1964: 571-584. A plea for differentiating social levels in sociological analysis and explanation.

71 WELZ, Rainer , `Probleme der Mehrebenenanalyse: Zum Versuch der Verbindung von Individual- und Kollektivdaten' (Problems of multi-level analysis: an attempt to relate individual with collective data), Soziale Welt, 25, 1974: 168-187. An article about the relationship between ecological and individual effects.

72 WIEGMAN, O. , Aanstekelijheid van Gedrag (Contagiousness of behaviour), Utrecht, Rijksuniversiteit, 1975.

73 YINGER, J.M. , Toward a field theory of behavior: personality and social structure, New York, McGraw Hill, 1965. Yinger illustrates the analytical approach in sociology by means of the question whether or not an individual tends `to discriminate against minorities if he lives in a community where authoritarian values prevail as opposed to one where they do not'.

74 ZIEGLER, Rolf, Theorie und Modell: Der Beitrag der Formalisierung zur soziologischen Theorie-bildung (Theory and model; the contribution of formalization to sociological theory formation), München/Wien, Oldenbourg, 1972: 160-79. A section, entitled `Einige Probleme der Kontekstund Mehrebenenanalyse' (some problems of contextual and multi-level analysis) contains a treatment of the `ecological fallacy', the estimation of individual and contextual effects, and measurement problems of aggregated variables.

75 ASTIN, Alexander W. , `The methodology of research on college impact', Sociology of Education, 43, 1971: 223-254 (part I); 43, 1971: 437-450 (Part II). In two articles a range of methodological problems are dealt with. In the first article the accent is on the design issue, and in the second on problems of collecting data and measuring environmental attributes of colleges.

76 BALES, Robert F. , Interaction process analysis. A method for the study of small groups, Cambridge, Mass., Addison-Wesley, 1950.

77 BARTON, Allen H. , `Personal influence revisited', Rivista di Sociologica, 6, 1968: 53-68. This paper examines cluster samples in order to assess social contexts, and sociometric samples in order to measure `interpersonal environments'.

78 BARTON, Allen H. , `Allen Barton comments on Hauser's “context and consex” ', American Journal of Sociology, 76, 1970: 514-517. Hauser's conclusion (see 187) that `contextual analyses are fruitless' is based on a violation of some basic rules of survey research (see also 188).

79 BERTRAM, Hans , `Probleme einer sozialstrukturell orientierten Sozialisationsforschung' (Problems of social structural-oriented socialization research), Zeitschrift für Soziologie, 5, 1976: 103-117. Research into class-determined socialization is stagnating. The causes are bad analysis of socio-structural conditions, intra-familial communication processes, and the concepts of individual behaviour.

80 BLALOCK, Hubert, M., jun. , `Status inconsistency, social mobility, status integration and structural effects', American Sociological Review, 32, 1967: 790-801. This article states that there are methodological similarities among four different sociological theories: (1) the status inconsistency approach; (2) theories concerning the effects of social mobility; (3) the Gibbs-Martin status-integration approach; and (4) the analysis of structural or compositional effects. In each of these theories there is the common notion that a dependent variable may be affected by deviance or particular combinations of status.

81 BLALOCK, Hubert M., jun. , `Status inconsistency and interaction: some alternative models', American Journal of Sociology, 73, 1968: 305-315. Several mathematical `models of inconsistency' are investigated in order to detect the assumptions; one of these is the structural-effects model.

82 BLAU, Peter M. , `Formal organizations: dimensions of analysis', American Journal of Sociology, 63, 1957: 58-69. Three methodological problems are discussed: `(1) the effects of group structure can be isolated by determining the relationship between X and Y for groups holding constant the independent variable X for individuals; (2) the quantitative study of complex configurations of interdependent elements involves the internal and external elaboration of a relationship between two major elements; and (3) dialectical processes characterize organizational change, and these processes may be empirically investigated by adapting the panel method to organizational research.'

83 BURSTEIN, Leigh , `The role of levels of analysis in the specification of educational effects' in: R. Dreeben and J.A. Thomas (eds), The analysis of educational behavior, Vol. I, Issues in micro-analysis, Cambridge, Boellingen, 1980: 119-190. The aim of the article is `to present a comprehensive treatment of the role of levels of analysis in the specification of educational effects'.

84 CATTELL, R.B. , `Concepts and methods in measurement of group-syntality, Psychological Review, 55, 1948: 48-63.

85 CATTELL, Raymond B. , SAUNDERS, R.B. , STICE, G.F. , `The dimensions of syntality in small groups', Human Relations, 6, 1953: 331-356. This study aims to develop a representative set of independent, primary dimensions of `syntality' on the basis of characteristics of typical Catholic groups.

86 COLEMAN, James S. , `Relational analysis: the study of social organization with survey methods', Human Organization, 27, 1958/59: 184-211. (Also in: Amitai Etzioni, Complex organizations, New York, Holt, Rinehart and Winston, 1961: 441-53.) The aim of this article is to describe some recent developments in survey research, relevant for the study of social organizations.

87 COLEMAN, James S. , Introduction to mathematical sociology, New York, Free Press, 1964.

88 COLEMAN, James S. , `Properties of collectivities' in: James S. Coleman, Amitai Etzioni and John Porter, Macrosociology: research and theory, Boston, Allan and Bacon, 1970: 5-101. An orderly treatment of how characteristics can be assessed, both on the collective level directly and in the constituent elements of the collectivity. The resulting insights are illustrated by several examples.

89 CRONBACH, Lee J. , WEBB, Noreen , `Between-class and within- effects in reported aptitude treatment interaction: reanalysis of a study by G.L. Anderson', Journal of Educational Psychology, 67, 1973: 717-724. In reaction to an investigation by G.L. Anderson, the importance of separating class, individual and individual-within-class interaction effects are discussed.

90 DAVIS, James A. , SPAETH, Joe L. , HUSON, Carolyn , `A technique for analyzing the effects of group composition', American Sociological Review, 26, 1961: 215-225. `A technique is proposed to isolate the contribution to the probability of occurrence of a dependent attribute of: (1) individual attributes, and (2) group composition in terms of members' attributes. A classification of possible types of relationships which can be identified by the technique is proposed, statistical problems are discussed, and two empirical examples are presented.'

91 DAVIS, James A. , `Contextual sex-saliency and sexual activity: the relative effects of family and peer groups in the sexual socialization process', Journal of Marriage and the Family, 36, 1974: 196-202. `Presents a nonrecursive simultaneous equation model for the formation of occupational aspirations. In the model, reciprocal effects between friends' and ego's aspirations are allowed.'

92 DURKHEIM, Emile , Les Règles de la Méthode Sociologique (The rules of sociological method), Paris, Presses Universitaires de France, 1950. [First edition 1892.]

93 EEDEN, Pieter van den , `Identification of a multi-level relationship' in: Gerard de Zeeuw and Pieter van den Eeden (eds), Problems of context, Amsterdam, VU-Boekhandel, 1979: 111-126. The question is asked `How to identify a multilevel relation?' The author specifies two classes of conditions: those concerning the proper multi-level relationship and those concerning the unit-variable relationship.

94 ELDER, Glen H., jun. , `Role relations, sociocultural environments, and autocratic family ideology', Sociometry, 28, 1965: 173-196. `The formation and reinforcement of autocratic ideology about the participation of youth in family decision-making are investigated in a secondary analysis of data from five nations which vary widely in cultural and institutional support for this belief.'

95 ELESH, David B. , Causation in contextual analysis, University Microfilms, Ann Arbor, Michigan, 1968. [Columbia University, PhD.] This study offers a systematic and critical survey of the different causal models that can be used in multi-level research.

96 FARKAS, George , `Specification, residuals and contextual effects', Sociological Methods and Research, 2, 1974, 333-363. `The controversy over contextual effects is reviewed from the standpoint of specification analysis. It is concluded that contextual effects are weak, but cannot be dismissed, and a new line of theorising is advocated.'

97 FELDMAN, Kenneth A. , `Some methods for assessing college impacts', Sociology of Education, 44, 1971: 133-150. The main methods for assessing the impacts of colleges on students are compared and discussed. Attention is paid to the conditions of the use of these methods.

98 FELDMAN, Kenneth A. , `The assessment of college impacts' in: Kenneth A. Feldman (ed.), College and student, New York, Pergamon Press, 1972: 211-225. This article aims to help the reader of studies on college impact to evaluate analyses, results and interpretations more meaningfully.

99 GAVIN, James F. , HOWE, John G. , `Psychological climate: some theoretical and empirical considerations', Behavioral Science, 20, 1975: 228-240. `One of the more important considerations arising from this study concerns the distribution between organizational and psychological climates.'

100 GLOCK, Charles Y. , `Survey design and analysis in sociology' in: Charles Y. Glock (ed.), Survey research in the social sciences, New York, Russell Sage Foundation, 1967: 44-49. A survey of several possible research designs, for example the `contextual design'.

101 GOLEMBIEWSKI, R.T. , The small group, an analysis of research concepts and operations, Chicago, 1962.

102 GOODMAN, Leo A. , `Ecological regressions and behavior of individuals', American Sociological Review, 18, 1953: 663-664. An addition to the well-known problem formulated by Robinson (337) and a treatment of the possibilities of predicting individual behaviour by means of ecological regressions.

103 GRAAF, C.J.A.W., de , `Multi-nivo analyse: problemen bij de analyse van gegevens van onderzoekseenheden van verschillend niveau' (Multi-level analysis: problems in the analysis of data from units of a different level of analysis), Sociale Wetenschappen, 16, 1973: 168-189.

104 HAGSTROM, Warren O. , SELVIN, Hanan C. , `Two dimensions of cohesiveness in small groups', Sociometry, 28, 1965: 30-43. `A factor analysis of 19 possible indicators of cohesiveness in 20 college living groups yields two dimensions, one labelled “social satisfaction” and the other “sociometric cohesion”.'

105 HALPIN, A.W. , Theory and research in administration, New York, 1966.

106 HARDER, Theodor , `Contextuality and dynamics', Zeitschrift für Soziologie, 3, 1974: 229-235. `The methodological problems of multi-level analysis are developed from an elementary statistical standpoint.'

107 HAUSER, Robert M. , `Contextual analysis revisited', Sociological Methods and Research, 2, 1974: 365-375. A comment on an article by Farkas, stressing several pitfalls in multi-level research (see 96).

108 HOPKINS, Terence K. , WALLERSTEIN, Immanual , `The comparative study of national societies', Social Science Information, 6, 1967: 25-58. A methodological discussion of cross-national research.

109 HÜTTNER, Harry J.M. , `De multi-level analyse: een toepassing en evaluatie van het model' (Multi-level analysis: an application and evaluation of the model), Sociologische Gids, 20, 1973: 42-58. By means of a study into work satisfaction of aspirant nurses an outline of multi-level analysis is given.

110 JACOBSEN, Chanoch , VOORDT, Theo van der , `Interpreting model frequencies to measure social norms', Sociological Methods and Research, 8, 1980, 470-486. `The empirical study of social norms has been hampered by a lack of standardised quantitative measures and criteria for the interpretation of research data. Two such criteria are suggested, both of them derived from the modal proportion of responses.'

111 KASARDA, John D. , `The structural implications of social system size: a three-level analysis', American Sociological Review, 39, 1974: 19-28. `This study examines the structural implications of social system size on three levels of the social system hierarchy: the institutional, the communal, and the societal. Cross-tabular and correlation analysis indicate that large size has a substantial influence on the internal organization of social systems at each level.'

112 KASARDA, John D. , `On social system properties: an alternative view', American Sociological Review, 39, 1974: 886-888. A reaction to Noell's comment (see 122) on an article written by Kasarda (see 111).

113 KNAPP, Thomas R. , `The unit-of-analysis problem in applications of simple correlation analysis in educational research', Journal of Educational Statistics, 2, 1977: 171-186. `This paper summarizes the interrelationships among within-aggregate, between-aggregate, and total-group correlation coefficients, with artificial and “real-data” examples. It also discusses the relevance of correlation analysis at various levels of aggregation and some of the difficulties encountered in cross-level inference.'

114 LAFFERTY, William M. , `Contexts, levels, and the language of comparison: alternative research', Social Science Information, 11, 1972: 63-91. `The major part of the discussion is devoted to two alternative multi-level research strategies, both of which attempt to solve the ideographic-nomothetic dilemma.'

115 LEENT, Johannes A.A. van , Sociologie, Psychologie en Sociale Psychologie: Hun Opbouw, Ontwikkeling en Verhouding vanuit Macro-micro Oogpunt (Sociology, psychology, and social psychology: their structure, development and relationship from a macro-micro point of view), Zeist, De Haan, 1964.

116 LINZ, Juan J. , `Ecological analysis and survey' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 91-131. A plea for research designs in which ecological analysis and survey research are combined.

117 LIPPIT, R. , WHITE, R. , `Reader behavior and members' reaction in three “social climates”, in: R. Cartwright and A. Zander (eds), Group Dynamics, New York, Harper and Row, 1968: 318-335.

118 MELTZER, Leo , `Comparing relationships of individual and average variables to individual response', American Sociological Review, 28, 1963: 117-123. `The attitudes of individuals, and the average attitudes of the groups of which they are members, are related to a number of dependent variables.'

119 MYERS, David G. , BACH, Paul J. , `SCHREIBER, F. Barry, `Normative and informational effects of group interaction', Sociometry, 37, 1974: 275-286. The `two-process explanation of group-induced shift' is supported with empirical material, although explanations of group shift based on group decision models are discussed.

120 MYERS, D.G. , LAMM, H. , `The polarizing effect of ground discussion', American Scientist, 63, 1975: 297-303.

121 NEHNEVAJSA, J. , `Soziometrische Analyse von Gruppen' (Sociometrical analysis in groups), Kölner Zeitschrift für Soziologie und Sozialpsychologie, 7, 1955: 119-157 and 280-302.

122 NOELL, James J. , `System level and system property', American Sociological Review, 39, 1974: 885-886. A comment on Kasarda's article (111).

123 NOWAK, Stefan , `The logic of reductive systematizations of social and behavioral theories' in: Stefan Nowak, Understanding and prediction: essays in the methodology of social and behavioral theories, Dordrecht, Holland/Boston, Mass., Reidel, 1967: 376-449. `The main task is the analyzing of certain problems of reduction (or reductive systematization of sociological theories) and clarifying the basic misunderstanding around the “problem of reduction” in sociology.'

124 PHILLIPS, David P. , CONVISER, Richard H. , `Measuring the structure and boundary properties of groups: some uses of information theory', Sociometry, 35, 1972: 235-254. `This paper presents a measure of structure drawn from information theory. This measure is used to determine the number of groups in the situation, to locate group boundaries and to determine the sharpness of those boundaries, and to measure the loss of descriptive accuracy in mislocating group boundaries.'

125 PICOU, J. Steven , CARTER, T. Michael , `Significant other influence and aspirations', Sociology of Education, 49, 1976: 12-22. `Data from a statewide probability sample of Louisiana high school seniors are used to assess causal effects of significant other influence on aspirations.'

126 POYNOR, Hugh , `Selecting units of analysis' in: G. Borich (ed.), Evaluating educational programs and products, Englewood Cliffs, NJ, Educational Technology Press, 1974: ch. 15.

127 SCHEUCH, Erwin K. , `The cross-cultural use of sample surveys: problems of comparability' in: Stein Rokkan (ed.), Comparative research across cultures and nations, Paris/The Hague, Mouton, 1968: 176-209. Discusses and criticizes different models of cross-national research organization and design. Emphasizes the dangers of an `ecological fallacy' in cross-national analyses. To avoid such fallacies it is essential to develop systematic measures of variation at several levels of each national unit.

128 SCHEUCH, Erwin K. , `Social context and individual behavior' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 133-155. A plea for combining the greater relevance of cross-level theorizing with the greater rigour of so-called direct measurement. In addition to the ecological fallacy, the `individualistic fallacy' is indicated.

129 SIROTNIK, Kenneth A. , `Psychometric implications of the unit-of-analysis problem (with examples from the measurement of organizational climate)', Journal of Educational Measurement, 17, 1980: 245-282. This paper presents (a) mathematical support for the potential between and within differences, (b) an almost universal avoidance of these differences in one body of literature, and (c) empirical evidence of these differences with respect to one `climate life' instrument.

130 STALLINGS, Robert A. , `Patterns of belief in social movements: classification from an analysis of environmental groups', The Sociological Quarterly, 14, 1973: 465-480. `Data from a total census of a focal group within one urban environmental coalition are presented and the distribution of beliefs across its structure described. The degree of homogeneity of beliefs decreases with movement from the center to the periphery of the group.'

131 SWANBORN, P. G. , Variabelen en hun Meting (Variables and their measurement), Meppel, Boom, 1973.

132 SWANBORN, Peter G. , `Schoolkenmerken en leerlinggedrag: enkele methodologische merkwaardigheden in het onderzoeksbedrijf' (School characteristics and pupil behaviour: some methodological issues in research praxis), Mens en Maatschappij, 53, 1978: 209-216. A plea for the random selection of the context-units in a multi-level analysis.

133 TAGIURI, R. , `The concept of organizational climate' in: R. Tagiuri and G.H. Litwin (eds), Organizational climate: exploration of a concept, Cambridge, Mass., Havard University Press, 1968.

134 TANNENBAUM, Arnold S. , BACHMAN, Gerald G. , `Structural versus individual effects', American Journal of Sociology, 69, 1964: 585-595. `Methods for separating the effects of group structure or composition from individual effects proposed by Blau [82] and by Davis, Spaeth and Huson [90] do not always hold individual or group characteristics strictly constant.'

135 TEUNE, Henry , `Cross-level analysis: a case of social inference', Quality and Quantity, 13, 1979: 527-537. `The purpose of this article is to argue that cross-level inference is logically equivalent to any other kind of social inference.'

136 WALKER, T.G. , MAIN, E.C. , `Choice shifts in political decision making: federal judges and civil liberties cases', Journal of Applied Social Psychology, 3, 1973: 39-48.

137 WELLER, Jack M. , QUARANTELLI, E.L. , `Neglected characteristics of collective behavior', American Journal of Sociology, 79, 1973: 665-685. `Closer and more fruitful relationships between theories of institutionalized behavior and theories of collective behavior depend in part on the development of a social-level conception of collective behavior. To this end the two forms of social organization are contrasted along the dimensions of social norms and social relationships. On these dimensions, a definition and a typology of collective behavior are suggested.'

138 ALEXANDER, C. Norman , CAMPBELL, Ernest Q. , `Peer influences on adolescent educational aspiration and attainments', American Sociological Review, 29, 1964: 568-575. In addition to relational, sociometric approaches in the investigation of study aspirations, the predicting value of the `balance model' is examined.

139 ALEXANDER, Karl L. , ECKLAND, Bruce K. , `Contextual effects in the high school attainment process', American Sociological Review, 40, 1975: 402-416. In this article the results of contextual effect on individual college plans are summarized in a `school process model of compositional effects'. `Ability' appears to exert a negative effect; the effect of `social-economic status' appears to be positive.

140 ALEXANDER, Karl L. , GRIFFIN, Larry J. , `School district effects on academic achievement: a reconsideration', American Sociological Review, 41, 1976: 144-152. A comment on the general utility of the Bidwell and Kasarda model on `academic achievement' (see 155). On the basis of findings in Maryland it is suggested that the model is mis-specified by the omission of student academic ability.

141 ALEXANDER, Karl L. , GRIFFIN, Larry J. , `Reply to Bidwell and Kasarda', American Sociological Review, 41, 1976: 755-762. A reply to some criticism by Bidwell and Kasarda on an article by Alexander and Griffin (see 156). It is pointed out that (a) district-to-district differences in academic achievement are in all likelihood very small; (b) even this small portion of the total achievement variance must be examined with appropriate theoretical models if misleading conclusions are to be avoided.

142 ALEXANDER, Karl L. , McDILL, Edward L. , `Selection and allocation within schools: some causes and consequences of curriculum placement', American Sociological Review, 41, 1976: 963-980. `A multivariate “school process” model is evaluated to explore the antecedents and consequences of curriculum enrollment.' The selection process within a school (`curriculum placement or enrollment') depends on `academic ability' and the social environment of the pupil. The characteristics of peer associates, academic performance, and curriculum enrollment contribute to the explanation of a number of individual orientations. The influence of background variables is exerted by those characteristics.

143 ALEXANDER, Karl L. , ECKLAND, Bruce K. , `High-school context and college selectivity: institutional constraints in educational stratification', Social Forces, 56, 1977: 166-188. A structural model of the process of influencing the choice for more or less academically selective colleges by the kind of high school is proposed. Data derived from a sample of 2,077 high school sophomores surveyed in 1955 and 1970 are analyzed separately by sex. When individual family background, ability, and school curriculum are controlled for, male students (but not female students) show prospects of attending a selective college, influenced by social status composition of high school.

144 ALEXANDER, Karl L. , McDILL, Edward L. , FENNESSEY, James, D'AMICO , Ronald J. , `School SES-influences — composition or context?', Sociology of Education, 52, 1979: 222-237. Using data on 3,050 students from 18 high schools, analyses were performed to distinguish the `contextual' effects of average socio-economic status levels across schools. The results indicate that after compositional differences are taken into account, the `contextual' effects of average socio-economic status level are inconsequential.

145 ALWIN, Duane F. , `Assessing school effects: some identities', Sociology of Education, 49, 1976: 294-303. A comparison of the contextual variable method and the covariance method for analyzing data in terms of a general school-effects model.

146 ALWIN, Duane F. , OTTO, Luther B. , `High-school context effects on aspirations', Sociology of Education, 50, 1977: 259-273. College plans and vocational aspirations are the only independent variables that are explained by environmental characteristics. Furthermore, differences between schools are explained by independent variables.

147 ANDERSON, Barry , TISSIER, Ronald M. , `Social class, school bureaucratization, and educational aspirations', Educational Administration Quarterly, 9, 1973: 34-47. An investigation into the relation between social class, organizational structure of a school and students' aspirations to continue their study.

148 ASTIN, Alexander W. , `Differential college effects on the motivation of talented students to obtain the Ph.D.', Journal of Educational Psychology, 54, 1963: 63-71. The relation between college characteristics and students' motivation to obtain a PhD is central in this study. It is investigated by using a longitudinal model in order to control the relevant individual input characteristics.

149 ASTIN, Alexander W. , `Comment on “a student's dilemma: big fish-little pond or little fish-big pond” ', Journal of Counseling Psychology, 16, 1969: 20-22. This article contains a discussion about some important theoretical issues in a study by Werts and Watley (see 225) about the effects of a college environment.

150 AVERCH, H. , CARROLL, S. , DONALDSON, T. , KIESLING, H. , PINCUS, J. , How effective is schooling? A critical review and synthesis of research findings, Santa Monica, Rand Corporation, 1972.

151 BAIN, Robert K. , ANDERSON, James G. , `School context and peer influences on educational plans of adolescents', Review of Educational Research, 44, 1974: 429-445. This review of recent studies indicates that the relationship between school social class composition and the college plans of students appears to involve a positive effect of the former upon the desire to attend college, which is transmitted through personal friends in school, and a negative effect upon self-perceived ability to attend college.

152 BAIRD, L.L. , `The practical utility of measures of college environments', Review of Educational Research, 44, 1974: 307-329. Reviewing environmental measures of college environments and making environmental measures more useful, are two goals carried out within a framework of four decision-making categories, requiring environmental information, considered from input, contextual and output perspectives.

153 BARTON, Allen H. , Organizational measurement and its bearing on the study of college environments, New York, College Entrance Examination Board, 1961. Several empirical studies on school systems are scrutinized for analytical, global, structural and contextual characteristics.

154 BASSIS, Michael S. , `The campus as a frog pond: a theoretical and empirical reassessment', American Journal of Sociology, 82, 1976: 1318-1326. By means of a path analysis it is demonstrated that students can obtain their academic self-evaluation not only by comparison of their own study results with those of their peer students. The prestige of the college in relation to other colleges is also incorporated in their analysis.

155 BIDWELL, Charles F. , KASARDA, John D. , `School districts' organization and student achievement', American Sociological Review, 40, 1975: 55-70. `Five environmental conditions of these districts, three components of district structure and one of staff composition are linked in a causal model to the median reading and mathematics achievement test scores of the districts' high school students.'

156 BIDWELL, Charles F. , KASARDA, John D. , `Reply to Alexander and Griffin', American Sociological Review, 41, 1976: 762-768. Alexander and Griffin are accused (a) of not distinguishing between ecological analysis and the individual level analysis containing contextual variables, and (b) of failing to genralize the point of ecological bias (see 140).

157 BLAU, Peter M. , `Levels and types of structural effects: the impact of university structure on professional schools' in: William E. Snizek , E.R. Fuhrman and M.K. Miller (eds), Contemporary issues in theory and research: a methodological perspective, London, Aldwych Press, 1979: 137-160. Higher order structural effects on organizational components appear to be explained by more or less the same principles as lower order structural effects (on individual behaviour).

158 BLAU, Peter M. , MARGULIES, Rebecca Z. , CULLEN, John B. , `The professional and academic context of professional schools' in: James S. Coleman , Peter Rossi and R.K. Merton (eds), Qualitative and quantitative research in sociology, New York, Free Press, 1979. Professional schools exist at the intersection of two institutions, the profession for which they supply training and the university to which they belong. In order to compare specific professional schools, generic attributes of both types of institutions mentioned are developed. On this basis an analysis of the influences exerted on American professional schools by their professional and academic context is carried out.

159 BOOCOCK, Sarane S. , `The school as a social environment for learning: social organization and micro-social process in education', Sociology of Education, 46, 1973: 15-50. `An attempted synthesis of the literature on the social organisation of schools and the interaction comprising the social process of education.'

160 BOUDON, Raymond , Education, opportunity, and social inequality, New York, Wiley, 1974. An empirical investigation in France into inequality of educational opportunity, inequality of social opportunity and social immobility.

161 BOWERS, William J. , `Comments to the editor', Sociology of Education, 39, 1966: 100-105.

162 BOWERS, William J. , `Normative constraints on deviant behavior in the college context', Sociometry, 31, 1968: 370-385. Normative constraints `on ten forms of deviant behavior among samples of students from 99 colleges' are examined. `Normative constraints are separated into individual and contextual disapproval.'

163 BOWLES, Samuel , LEVIN, Henry , `The determinants of scholastic achievement: an appraisal of some recent evidence', The Journal of Human Resources, 3, 1968: 3-24. An attack on the reliability and the validity of the research methods and results of the so-called Coleman Report (see 174).

164 BOYLE, Richard P. , `The effect of the high school on student's aspirations', American Journal of Sociology, 71, 1966: 628-639. Some inconsistencies in the relationship between `aspirations of students and the kind of school they attend' are controlled for `high schools in large metropolitan areas and those in smaller communities'.

165 BOYLE, R.P. , `On neighbourhood context and college plans (III)', American Sociological Review, 31, 1966: 706-707. A critical comment on Sewell and Armer (see 216).

166 BRESLAUER, S.D. , `Some contextual variables in student response to university-level study of Jewish mysticism', Review of Religious Research, 16, 1975: 221-226. `This study seeks to offer some data that may illuminate the relationship of academic courses in Judaica and the American Jewish search for identity. It is suggested that the differences between the students' perceptions reflect the differing needs revealed in their contexts.'

167 BURSTEIN, Leigh , FISCHER, Kathleen B. , MILLER, M. David , `The multi-level effects of background on science achievement: a cross-national comparison', Sociology of Education, 53, 1980: 215-225. It is demonstrated that an examination of the multi-level effects of background is warranted as the effects of family background on science achievement are the result of various processes between and within schools.

168 CAIN, Glen C. , WATTS, Harold W. , `The controversy about the Coleman report: comment', Journal of Human Resources, 3, 1968: 389-392. See 169 and 174.

169 CAIN, Glen C. , WATTS, Harold W. , `Problems in making policy inferences from the Coleman report', American Sociological Review, 35, 1970: 228-242. `The principal theme of this paper is that the analytical part of the Coleman Report (see 174) has such serious methodological shortcomings that it offers little policy guidance: (1) the specification of the theoretical model is inadequate and thus there is no way to interpret Coleman's statistical results; (2) when the Coleman Report does make clear the justification for the use of a variable in the regression model, the criterion used to assess the statistical performance of the variable (namely, its effect on R2) is inappropriate.'

170 CAMERON, Kim , `Measuring organizational effectiveness in institutions of higher education', Administrative Science Quarterly, 23, 1978: 604-632. `Some obstacles to the assessment of organizational effectiveness in higher education are discussed, namely criteria problems and the unique organizational attributes of colleges and universities, and criteria choices addressing these issues are outlined. Criteria were generated from dominant coalition members in six institutions, and nine dimensions of organizational effectiveness were derived.'

171 CARROLL, Jackson W. , `Structural effects of professional schools on professional socialization: the case of protestant clergymen', Social Forces, 50, 1971: 61-74. By means of Blau's method of analyzing structural effects it is demonstrated that `the structure of the schools is related to theological orientation in the predicted direction even when additional variables are introduced into the analysis'.

172 CHEN, Michael , FRESKO, Barbara , `The interaction of school environment and student traits', Educational Research, 20, 1978: 114-121. `School climate, defined here as the type of mobility system reflected in the school's selection procedures, was shown to interact with ethnic group membership and locus of control (after SES factors were controlled) in affecting student achievement in Israeli schools. The achievement of the socially higher status group was found to be more sensitive to changes in the school atmosphere than that of the lower status group.'

173 COLEMAN, James S. , `The adolescent subculture and academic achievement', American Journal of Sociology, 65, 1960: 337-347. This paper tests the hypothesis which implies that in an `adolescent social system in which academic achievement is highly valued, those who achieve highly will include more people whose actual intelligence is high than in a social system where this activity is less valued.'

174 COLEMAN, James S. , `Pupil achievement and motivation' in: James S. Coleman, Ernest Q. Campbell, C.J. Hobson, J. MacPartland, A.M. Mood, F.D. Weinfeld and R.L. York, Equality and educational opportunity, Washington DC, 1966: 218-233. In the well-known Coleman Report, Coleman wrote on the relative importance of home-background factors and school variables vis-à-vis pupil achievement and motivation.

175 COLEMAN, James S. , `Reply to Cain and Watts', American Sociological Review, 35, 1970: 242-249. The differences between the scientific approach of Cain and Watts on the one hand and that of the authors of the Coleman Report on the other explain to a great extent Cain and Watt's criticisms of the Coleman Report (see also 169).

176 COLEMAN, Peter , `The improvement of aggregate teaching effectiveness in a school district', Educational Administration Quarterly, 9, 1973: 28-47. `This article proposes a teacher evaluation scheme utilising dimensions of teacher behavior which have been shown to be directly related to high levels of positive achievement and attitudes in students.'

177 DAVIS, James A. , `Compositional effects, role systems, and the survival of small discussion groups', Public Opinion Quarterly, 5, 1961: 574-584. An investigation of the influence of contextual variables on interactions in small groups did not yield the expected results: `they appeared heavily affected not by role quality, but by the quantitative climate of role participation'. This relation is better explained by `the content of interpersonal relations outside the groups'.

178 DAVIS, James A. , `Intellectual climates in 135 American colleges and universities: a study in “social psychophysics” ', Sociology of Education, 37, 1963: 110-128. Analysis of campus differences in the proportion of seniors who endorse intellectual values (`true climate of intellectualism') and the proportion who see their classmates as having intellectual values (`perceived climate of intellectualism').

179 DREW, David E. , ASTIN, Alexander W. , `Undergraduate aspirations: a test of several theories', American Journal of Sociology, 77, 1972: 1151-1164. In this study the theory of relative deprivation and the theory of group pressure are investigated in order to explain study aspirations. It appeared that the relative deprivation theory is more valid than the group pressure theory.

180 DUNCAN, Otis D. , `Duncan's corrections of published text “Peer influences on aspirations: a reinterpretation” ', American Journal of Sociology, 75, 1970: 1042-1046. See 181.

181 DUNCAN, Otis D. , HALLER, A.O. , PORTES, A. , `Peer influences on aspirations: a reinterpretation', American Journal of Sociology, 74, 1968: 119-137. By means of path diagrams and `equation systems involving simultaneous or joint dependent variables' the hypothesis is tested which states that there is a mutual relationship between the `best friends' educational and occupational aspiration' and `ego's aspirations'.

182 GROOT, Adriaan D. de , Vijven en Zessen: Cijfers en Beslissingen: Het Selectieproces in het Onderwijs (Fives and sixes: rates and decisions: the process of selection in education), Groningen, Wolters-Noordhoff, 1966.

183 HALLER, Archibald O. , OTTO, Luther B. , MEIER, Robert F. , OHLENDORF, George W. , `Level of occupational aspiration: an empirical analysis', American Sociological Review, 39, 1974: 113-121. Comparable analyses were performed in a total sample of high school students and sixteen sub-samples from it cross-classified by sex, SES, and grade. The impact of the level of occupational aspiration remains the same in all samples.

184 HALLINAN, Maureen T. , `Friendship patterns in open and traditional classrooms', Sociology of Education, 49, 1976: 254-265. This study shows that traditional school classes are hierarchically built and based on popularity, and that open school classes possess a more uniform distribution. In open classes there are fewer lone students, and the duration of friendships is longer.

185 HALLINAN, Maureen T. , TUMA, Nancy Branton , `Classroom effects on change in children's friendships', Sociology of Education, 51, 1978: 270-282. It is argued and proven `that the way teachers group students for instructional purposes and their pedagogical techniques affect children's proximity and similarity within the classroom, and that these in turn affect their interpersonal relationships'.

186 HAUSER, Robert M. , `Schools and the stratification process', American Journal of Sociology, 74, 1968/69: 587-611. `The influence of socioeconomic origins on three outcomes of secondary schooling is interpreted using path analysis and covariance analysis.'

187 HAUSER, Robert M. , `Context and consex: a cautionary tale', American Journal of Sociology, 75, 1969/70: 645-664. `Covariance analysis and dummy-variable regression analysis are advocated as more suitable techniques for the measurement and interpretation of differences among groups.' Contextual effects are described as artefacts.

188 HAUSER, Robert M. , `Reply to Barton's comment on Hauser's context and consex', American Journal of Sociology, 76, 1970: 517-520. See 78.

189 HAUSER, Robert M. , `Disaggregation: a social-psychological model of educational attainment', Social Science Research, 1, 1972: 159-188. (Reprinted in: Arthur Goldberger and Otis D. Duncan (eds), Structural equation models in the social sciences, New York/San Francisco/London, Academic Press, 1973.) `This paper gives an extended empirical treatment of the estimation and interpretation of a block-recursive social-psychological model of socio-economic achievement which is applied to a cohort of male Wisconsin high school graduates.'

190 HEAL, Kevin , SINCLAIR, Ian , TROOP, Jane , `Development of a social climate questionnaire for use in approved schools and community homes', British Journal of Sociology, 24, 1973: 222-235. `This study describes the development of a questionnaire to assess the ways boys in approved schools perceive their social environment.'

191 HERRIOT, R.E. , MUSE, D.W. , `Methodological issues in the study of school effects' in: Fred N. Kerlinger (ed.), Review of research in education I, Itasca, Ill., P.E. Peacock Inc., 1973: 209-236. The discussion is concerned primarily with methodological issues in the study of educational effects.

192 KAHN, Roger M. , BOWERS, William J. , `The social context of the rank and file student activist: a test of four hypotheses', Sociology of Education, 43, 1970: 38-55. It appeared that four hypotheses could be confirmed. The hypotheses concern the backgrounds of rank-and-file student activists: they have grown up in higher SES families, are found in social faculties, are `good' students and possess strong intellectual orientations.

193 KAMENS, David H. , `The college “charter” and college size: effects on occupational choice and college attrition', Sociology of Education, 44, 1971: 270-296. In this study the effect of the size of colleges on the drop-out rate of students is investigated. It appears that big colleges possess a lower drop-out rate than small colleges. Probably the reason for this is the amount of prestige big colleges have and therefore the chance for better jobs.

194 LABOWITZ, Eugene M. , `Fulfilment of college aspirations: a simple causal analysis', Pacific Sociological Review, 17, 1974: 379-397. `This study combines structural effects and individual attributes into a single process model and focuses on the influence of structure and individual factors on college attendance of high school students.'

195 LABOWITZ, Eugene M. , `Race, SES context, and fulfilment of college aspirations', The Sociological Quarterly, 16, 1975: 241-249. `The differential effects of social contexts and race on educational behavior are examined in terms of a causal process model, utilizing both correlational and tabular techniques.'

196 LACY, William B. , `Interpersonal relationships as mediators of structural effects: college student socialization in a traditional and experimental university environment', Sociology of Education, 51, 1978: 201-211. `College student change on values, intellectual orientation, and personal development was analyzed in the context of a causal model. The research was based on a longitudinal panel study. The results indicated that college impact on students in different environments was mediated through the process of human interaction with socializing agents.'

197 LARKIN, Ralph W. , `Contextual influences on teacher leadership styles', Sociology of Education, 46, 1973: 471-479. `In a study of 75 Southern California classrooms, it was found that both the demographic context and the internal organization of the school had strong influences on the perceived classroom leadership styles of the teachers in it.'

198 LAZARSFELD, Paul F. , THIELENS, Wagner, jun. , The academic mind, Glencoe, Ill., Free Press, 1958. This investigation, carried out during the period of McCarthyism in the USA, studies teachers at the social faculties of several colleges. This period was characterized by a veritable witchhunt for alleged communists. The teachers were apprehensive about their personal freedom, and feared that academic freedom in general would be endangered. This study seeks to determine whether their apprehension is caused by individual personality characteristics or by their social environment.

199 LEVIN, Michael L. , `Social climates and political socialization', Public Opinion Quarterly, 25, 1961: 596-606. The aim of this project is to state the extent to which the political preferences of students have been influenced by home background, school and society. It appeared that home background is the most important factor.

200 McDILL, Edward L. , COLEMAN, James S. , `High school status, college plans, and interest in academic achievement: a panel analysis', American Sociological Review, 28, 1963: 905-918. An attempt to distinguish systematically the individual level, the group level and the societal level in studies into academic achievement.

201 McDILL, Edward L. , COLEMAN, James S. , `Family and peer influences in college plans of high school students', Sociology of Education, 38, 1965: 112-126. An attack on all studies `which show that the most important source of variation in educational aspirations is the child's socio-economic background'.

202 McDILL, Edward L. , MEYERS, Edmund D., jun. , RIGSBY, Leo C. , `Institutional effects on the academic behavior of high school students', Sociology of Education, 40, 1967: 181-199. Active attention by parents paid to the quality of education is the most pervasive source of differences in school climate and school achievement.

203 McDILL, Edward L. , RIGSBY, Leo C. , MEYERS, Edmund D., jun. , `Educational climates of high schools: their effects and their sources', American Journal of Sociology, 74, 1969: 567-586. The relevance of a number of current research variables is investigated and the educational implications of the results are discussed.

204 MEYER, John W. , `High school effects on college intentions', American Journal of Sociology, 76, 1970: 59-71. The author `tested the contention that the social status of a high school independently affects the college-going intentions of its students, using data from a 1955 sample of students in 518 American high schools.'

205 MICHAEL, J.A. , `On neighbourhood context and college plans (II)', American Socioligical Review, 31, 1966: 702-706. A critical outline on the relationship between SES and educational aspirations of pupils (see 276).

206 MOOS, Rudolph , MOOS, Bernice S. , `Classroom social climate and student absences and grades', Journal of Educational Psychology, 70, 1978: 263-269. The results of an investigation into factors that explain absenteeism `are discussed in their implications for understanding the differential effects of classes, as well as for identifying and changing high-risk classroom environments'.

207 MOOIJ, Ton , `Multi-level onderzoek van samenwerking in het parttime-onderwijs' (Multi-level research into collaboration in the part-time education), Mens en Maatschappij, 55, 1980: 148-179. `In this article multi-level analysis is carried out in a research project about regional cooperation between two part-time educational types. Four levels are presented, whilst three levels (individual, institutional, regional) are analysed.'

208 NASATIR, David N. , `A contextual analysis of academic failure', The School Review, 71, 1963: 290-298. `Though the effect upon individual students differs, the consequences of a particular group attribute for the process of failure — say a favorable orientation to academic standards — can be seen simply by comparing the rate of failure of its members with the rate for otherwise similar groups lacking such an orientation.'

209 NASATIR, David N. , `A note on contextual effects and the political orientation of university students', American Sociological Review, 33, 1968: 210-219. `By use of an analysis of variance technique, the independent effect that variation in the contexts of learning has upon students' political behavior is demonstrated.'

210 OTTO, Luther B. , `Extra curricular activities in the educational attainment process', Rural Sociology, 40, 1975: 162-176. An empirical support of Spady's hypothesis `that extent of participation in high school extra-curricular activities has a salutary effect on educational attainment statistically controlled on background SES, academic ability and performance'.

211 OTTO, Luther B. , ALWIN, Duane F. , `Athletics, aspirations, and attainments', Sociology of Education, 42, 1977: 102-113. An attempt to cross-validate `research supporting the hypothesis that perceived peer status mediates the effects of athletics on educational aspirations and attainments'.

212 PACE, C.R. , STERN, G.G. , `An approach to the measurement of psychological characteristics of college environments', Journal of Education Psychology, 49, 1958: 269-277. An attempt to develop measures of `college environment' derived from Murray's `need' and `press' categories.

213 PAVALKO, Ronald M. , `Recruitment to teaching: patterns of selection and retention', Sociology of Education, 43, 1973: 340-353. This study investigates the extent to which the SES of the group, and community-size (besides intelligence, ambition and marital status) exert influence on becoming a teacher and remaining a teacher. Community size did not have any impact on the choice of becoming a teacher. Women from small communities tend to stay in the teaching profession. SES influences the choice of becoming a teacher, but it does not influence the decision to remain one.

214 RIGSBY, Leo C. , McDILL, Edward L. , `Adolescent peer influence processes: conceptualization and measurement', Social Science Research, 1, 1972: 305-321. `Starting from the theoretical literature on interpersonal influence, this paper raises questions regarding what measurement strategies can be usefully employed to assess the import of peer influence processes on scholastic behavior of high school students.'

215 SEWELL, William H. , `Community of residence and college plans', American Sociological Review, 29, 1964: 24-38. In a study at Wisconsin high schools it appeared that `with each increase in community size category, the percentage of students with college plans increases. Intelligence and socio-economic status explain most of the differences among girls. Residential differences are most marked for boys in the high intelligence and socio-economic status categories.'

216 SEWELL, William H. , ARMER, J. Michael , `Neighbourhood context and college plans', American Sociological Review, 31, 1966: 159-168. `The popular thesis that neighborhood SES exerts considerable influence on educational aspirations of youth is examined. The evidence of this study suggests that past claims for the validity of this thesis may have been overestimated.'

217 SMITH, Robert B. , `Neighbourhood context and college plans: an ordinal path analysis', Social Forces, 51, 1972: 199-217. A re-analysis of data previously analyzed by Sewell and Armer (see 216) via an ordinal path analysis. Neighbourhood context has important effects on college plans, both directly and indirectly.

218 SØRENSEN, Aage B. , HALLINAN, Maureen T. , `A reconceptualization of school effects', Sociology of Education, 50, 1977: 273-289. `This paper presents a conceptual framework for the analysis of school effects on learning', starting from a learning theory.

219 SPADY, William G. , `The impact of school resources on students' in: Fred N. Kerlinger (ed.), Review of research in education I, Itasca, Ill., P.E. Peacock Inc., 1973: 135-177. (Reprinted in: William H. Sewell, Robert M. Hauser and David L. Featherman (eds), Schooling and achievement in American society, 1976: 179-84.) The question `do measurable differences in the characteristics of schools lead to measurable differences in student outcomes?' is treated in the context of educational resources allocation among schools and the allocation of student resources among schools.

220 SPENCER, William A. , `Interpersonal influences on educational aspirations: a cross cultural analysis', Sociology of Education, 49, 1976: 41-46. `This article, using Bolivian data to test a model based on American theoretical formulations, shows that structural factors exert little influecne on aspirations, apart from that mediated by the influence of significant others.'

221 THISTLEWAITE, Donald L. , WHEELER, Norman , `Effects of teacher and peer subculture upon student aspirations', Journal of Educational Psychology, 57, 1966: 35-47. The authors formulate which environmental pressures involve class norms and their influence on student's study aspirations.

222 THORNTON, Clarence H. , ECKLAND, Bruce K. , `High school contextual effects for black and white students: a research note', Sociology of Education, 53, 1980: 247-252. `Based on past research, it is predicted that the influence of school SES composition will be primarily salutory, while the influence of school ability context will be negative. Further it is predicted that these offsetting influences interact with race. General support is found for both sets of hypotheses.'

223 TURNER, Ralph H. , `On neighbourhood context and college plans (1)', American Sociological Review, 31, 1966: 698-702. In order to explain contrasting research findings, the presuppositions of the original projects are formulated (see also 216).

224 WEGNER, Eldon L. , SEWELL, William H. , `Selection and context as factors affecting the probability of graduation from college', American Journal of Sociology, 75, 1970: 665-679. `This study focuses on the relation of type of college attended to graduation as a factor in the educational selection process.'

225 WERTS, Charles E. , WATLEY, Donivan J. , `A student's dilemma: big fish-little pond or little fish-big pond', Journal of Counseling Psychology, 16, 1969: 14-17. A model for testing the contrasting predictions of the relative deprivation theory and the environmental pressure theory, and some preliminary evidence favouring relative deprivation theory are presented.

226 WILSON, Alan B. , `Residential segregation of social classes and aspirations of high-school boys', American Sociological Review, 24, 1959: 836-845. This article primarily poses the question of whether or not `the socio-economic context of the high school does affect the educational aspirations of boys, independently of their own socio-economic status'.

227 YUCHTMAN, Ephraim , YITZHAK, Samuel , `Determinants of career plans: institutional versus interpersonal effects', American Sociological Review, 40, 1975: 521-531. This article studies the effects of institutional and interpersonal influences upon career plans among Israeli youth. Two types of educational systems are compared: the `sponsored mobility system' and the `contest-oriented system'. In the sponsored mobility system students with a high-capacity level are segregated early on from other students and sent to schools that educate them properly for a license to attend university. Here the influence of significant others appeared to be less important than expected.

228 BUTLER, David , STOKES, Donald , Political Change in Britain, London/New York, Macmillan and St Martin's Press, 1969. Pages 134-150 investigate the extent to which the percentage of Labour votes depends on the percentage of blue-collar workers in that area. Areas with nearly the same percentage of Labour votes were compared with the percentage of `middle class' and `working-class' people. The data warrant the conclusion that party voting depends on `variations of party support by class' to a greater extent than on the `class composition' of that area.

229 COX, Kevin R. , `The spatial structuring of information flow and partisan attitudes' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 157-185. The aim of this contribution is, firstly, to identify certain contentious issues in recent contextual analysis of political behaviour and to suggest some alternative interpretations and solutions; secondly, to present five hypotheses summarizing these new interpretations and solutions and to test these using data collected in the Columbus metropolitan area of Ohio.

230 COX, Kevin R. , `Voting in the London suburbs: a factor analysis and a causal model' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 343-369. This investigation assesses the influence of physical characteristics of dwelling environment and personal characteristics on voting behaviour. Two theories seem to be relevant: the transplantation theory and the conversion (or transformation) theory. A preference for either is not expressed.

231 COX, Kevin R. , `The spatial components at urban voting response surfaces', Economic Geography, 47, 1971: 27-35. The author verifies a hypothesis about the neighbourhood impact upon the growth of a city. Neighbourhood context is measured by the proportional democratic vote.

232 CREWE, Ivor , `The politics of “affluent” and “traditional” workers in Britain: an aggregate of data analysis', British Journal of Political Science, 3, 1973: 29-52. This paper demonstrates that in a study of ballot voting it is possible to make use of the `residuals' as a technique in the analysis, and of the sample census as an important source of data.

233 CREWE, Ivor , PAYNE, G. , `Another game with nature: an ecological regression model in the British two-party vote ratio in 1970', British Journal of Political Science, 6, 1976: 43-81. One aim of the article is `to approach the old problem of ecological inference by means of an ecological regression analysis'.

234 DAVIES, P. , NEWTON, K. , `An aggregate data analysis of turnout and party voting in local elections', Sociology, 8, 1974: 213-231. `A partial correlation and multiple regression analysis of local elections in a large English city shows that class, housing tenure, age and coloured immigrants are closely related to voting patterns of total electorates, but geographical mobility and density of housing occupation are not.'

235 DOGAN, Mattei , `A covariance analysis of French electoral data' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 285-298. An example is given of the possibility of eliminating the disturbing effect of a variable by means of covariance analysis.

236 ENNIS, Philip H. , `The contextual dimension in voting' in: William McPhee and William A. Glaser (eds), Public opinion and congressional elections, New York, Free Press, 1962: 180-211. This article offers a description of a comparative and contextual investigation, using a large number of examples of contextual effects between characteristics of various collective (political, demographic and local) variables and individual characteristics.

237 FALTER, Jürgen W. , `The climate of opinion as a contextual determinant of political behavior: an analysis of the 1970 Saar State elections', European Journal of Political Research, 7, 1979: 147-167. By means of a variety of indicators Falter empirically tested the following hypotheses (a) `persons having interpersonal contacts at the local level should be more affected by contextual norms than persons without such contacts', and (b) `individuals obtaining their political information mainly through interpersonal contacts should be more susceptible to context norms than those who rely more on the mass media'. The results confirm these expectations.

238 FELDMAN, Kenneth A. , `Studying the impacts of colleges on students', Sociology of Education, 42, 1969: 207-237. `This paper attempts a broad overview of the research on college impact by outlining the ways in which such research has been done, pointing out the theoretical orientations and analytic strategies underlying the concomitant methodological problems and research issues.'

239 HARDER, Theodor , PAPPI, Franz Urban , `Multi-level regression analysis of survey and ecological data', Social Science Information, 8, 1969: 43-67. `The primary feature of secondary analysis is the integration of different sets of data with the purpose of ex post facto experimentation, i.e. discovery and testing. From this follows a natural link-up between multi-level and secondary analysis.'

240 KNOKE, David , `A causal synthesis of sociological and psychological models of American voting behavior', Social Forces, 53, 1974: 92-101. `A path model of the presidential vote involving social variables, party identification, issues orientations, and candidate evaluations is estimated using samples from the 1964 and 1968 elections. Social effects on voting behavior are channeled almost completely through party identification, which has the largest direct effect on the vote.'

241 LAZARSFELD, Paul F. , BERELSON, Bernard , GAUDET, Hazel , The people's choice, New York, Duell, Sloan and Pearce Inc., 1944. This study investigates the major influences upon voting behaviour during the presidential campaign of 1940. It highlights all those conditions and peer influences that determined the political behaviour of people during that campaign.

242 LIPSET, Seymour M. , TROW, Martin A. , COLEMAN, James S. , Union democracy. The international politics of the International Typographic Union, New York, Doubleday, 1956. This book examines the extent to which inconsistencies between individual political preferences and actual votes might be explained by the political composition of workers' environments.

243 McHALE, Vincent E. , PARTCH, Richard T. , `Canonical ecology and the analysis of aggregate voting models', Quality and Quantity, 9, 1975: 245-264. `Canonical correlation analysis is introduced as a method for coping with ecological complexity in the analysis of aggregate voting models.'

244 MILLER, William L. , `Measures of electoral change using aggregate data', Journal of the Royal Statistical Society, 135, 1972: 122-142. `A measure of electoral change should ideally have a simple interpretation both at the individual and aggregate level. This requirement is fulfilled by the matrix of transition votes between parties where each transition rate is a function of the local constituency partisanship. To estimate these transition votes from aggregate data, ridge regression is used to mitigate effects of multi-collinearity in the data.'

245 MILLER, William L. , Electoral dynamics in Britain since 1918, Basingstoke, Macmillan, 1977. An explanation of the actual ballot choices of certain electoral categories in relation to several categories of individuals.

246 PRZEWORSKI, Adam , SOARES, Glaucio A.D. , `Theories in search of a curve: a contextual interpretation of left vote', American Political Science Review, 65, 1971: 51-68. The central subject of this study is the propensity of an individual to vote for a left-wing party given the social context of his interactions.

247 PRZEWORSKI, Adam , `Contextual models of political behavior', Political Methodology, 1, 1974: 27-60. `This paper presents a class of models which share as their basic postulate the hypothesis that individual behavior depends upon the context within which it takes place.'

248 PUTNAM, Robert D. , `Political attitudes and the local community', The American Political Science Review, 60, 1966: 640-654. The ballot choice is neither determined by the activities of a party organization, nor by conformity to suspected community norms, but by social interaction.

249 RANNEY, Austin , `The utility and limitations of aggregate data in the study of electoral behavior' in: Austin Ranney (ed.), Essays on the behavioral study of politics, Urbana, Ill., University of Illinois Press, 1962: 91-102.

250 RETZLAFF, R.H. , `The use of aggregate data in comparative political analysis', Journal of Politics, 27, 1965: 797-817. `In order to assess progress in developing analytic models, conceptual schemes and methods of four essays are considered which have been widely cited as important examples of the use of aggregate data in comparative political analysis'.

251 ROKKAN, Stein , `The comparative study of political participation: notes toward a perspective on current research' in: Austin Ranney (ed.), Essays on the behavioral study of politics, Urbana, Ill., University of Illinois Press, 1962: 47-90. Four types of analysis are offered: (1) micro-micro, (2) macro-micro, (3) micro-macro, and (4) macro-macro. These `four levels of a political system' are combined with specific variables.

252 SWEETSER, Frank L. , `Ecological factors in metropolitan zones and sectors' in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 413-456. Based on data from the writer's studies of social ecology in metropolitan Boston and in the Helsinki metropolitan region, selected interzonal, intersector, and cross-national comparisons of factor profiles have been described as a basis for some tentative generalizations about types of ecological factors.

253 TINGSTEN, H. , Political behavior: studies in election statistics, London, P.S. King and Son, 1937.

254 VALKONEN, Tapani , `Community context and politicization for individuals', Acta Sociologica, 12, 1969: 144-155. This paper concentrates on the type of contextual effect which is seemingly most common: the contagion effect.

255 WASSERMAN, Ina M. , `State policy outputs and collective behavior: a causal reinterpretation', Social Science Quarterly, 59, 1978: 379-385. This paper evaluates the conclusions of a recent study which links political disaffection in the US to substantive and symbolic state policy outputs over time, as well as with collective behaviour.

256 ACKERMAN, C. , `Affiliations: structural determinants of differential divorce rates', American Journal of Sociology, 69, 1963: 13-20. Divorce rates are related to the structural characteristics of endogamy and exogamy.

257 BEARD, Donald W. , `The structure of organizational environments: a factor analytic approach', Organization and Administrative Sciences, 8, 1977/78: 85-105. The question is asked whether or not three extensive environmental characteristics of a production organization could be composed via a factor analysis procedure from variables, validated in previous studies.

258 BISHOP, Lloyd K. , GEORGE, Julius R. , `Organizational structure: a factor analysis of structural characteristics of public elementary and secondary schools, Educational Administration Quarterly, 9, 1973: 66-80. `This paper reports an attempt to develop a comprehensive instrument for the analysis and quantitative measurement of organizational characteristics within elementary and secondary schools.'

259 BLAU, Peter M. , The dynamics of bureaucracy: a study of interpersonal relations in two government agencies, Chicago, University of Chicago Press, 1955. [Revised edition 1964.] Formal bureaucratic organizations are analyzed in terms of interpersonal interaction structures, which constitute a dynamic element in a bureaucracy. The differences between individual and collective phenomena are investigated. In this new edition a section entitled `Implications for Study of Group Structure' has been added, in which the concept of `structural effect' is elaborated.

260 BLAU, Peter M. , `Orientation toward clients in a public welfare agency', Administrative Science Quarterly, 5, 1960: 341-361. An investigation into the influence of bureaucratic pressure on the ways in which newcomers in a public welfare agency do their work in comparison with their colleagues.

261 BLAU, Peter M. , `Patterns of choice in interpersonal relations', American Sociological Review, 27, 1962: 41-55. An investigation into the influence of individual characteristics on interpersonal choices in task groups. Four types of interpersonal choice patterns are determined and correspond to four patterns of influence.

262 BLAU, Peter M. , HEYDEBRAND, Wolf V. , STAUFFER, R.E. , `The structure of small bureaucracies', American Sociological Review, 31, 1966: 179-191. `A sophisticated multi-variate analysis of 156 public personnel agencies leads to a number of valuable generalizations about the nature of bureaucracy.'

263 BLAU, Peter M. , `Structural constraints of status complements' in: Lewis A. Coser (ed.), The idea of social structure: papers in honor of Robert K. Merton, New York, Harcourt, Brace, Jovanovich, 1975: 117-138. In this contribution Blau combines the concept of `status complement' with elements of Merton's concepts of `status set' and `role set' in order to define the treatment of structural effects.

264 CARLIN, Jerome E. , Lawyer's ethics: a survey of the New York City bar, New York, Russell Sage Foundation, 1966.

265 CHARDE, Patricia Marie , A contextual analysis of communication networks in a metropolitan area, Ann Arbor, Michigan, University Microfilms Inc., 1970. [Los Angeles, University of California, PhD.] The effects of social structure on communicative behaviour of individuals in a metropolitan area are investigated.

266 CLOWARD, Richard A. , OHLIN, Lloyd E. , Delinquency and opportunity: a theory of delinquent gangs, New York, Free Press, 1966.

267 COLEMAN, James S. , KATZ, Eric , MENZEL, Herbert , `The diffusion of an innovation among physicians, Sociometry, 20, 1957: 253-269. The prescription of a new drug depends not only on the individual characteristics of physicians, but also on the manner in which they are involved in the interaction structure with their fellow colleagues.

268 DAVIS, James A. , Great books and small groups, New York, 1961. The drop-out in small discussion groups is explained by both individual characteristics and group characteristics.

269 DURKHEIM, Emile , Suicide, translated by J.A. Spaulding and G. Simpson, Glencoe, Ill., Free Press, 1951. [First edition 1898.] One of the first contextual analyses, in which characteristics of populations and individuals are used in order to explain the social phenomenon of suicide.

270 ELKIN, Stephan L. , PANNING, William H. , `Structural effects and individual attitudes: racial prejudice in English cities', Public Opinion Quarterly, 46, 1973: 371-395. `Responses to a questionnaire concerning attitudes of English citizens toward “colored immigrants” provided the data for the analysis of the differential impact of social context on individual opinions.'

271 FARIS, R.E. , DUNHAM, H. Warren , Mental disorders in urban areas, Chicago, Ill., University of Chicago Press, 1939: 110-123. This project assesses the relationship between the type of city quarter and mental deviance. Disorganization of the quarter results in more cases of schizophrenia. This fact appears to be related to the type of quarter and not to the type of population. For manic depression, this relationship is not present.

272 FLINN, William L. , `Influence of community values on innovativeness', American Journal of Sociology, 75, 1970: 983-991. `This study attempts to illustrate the influence of structural effects on innovativeness. Several methods are used to isolate the external constraints and community values from the individual's internalized values and personal attributes. Data from seven truck-crop-growing communities suggest that either analytical constructed community values or perceived community values have an effect upon farmer's innovativeness.'

273 GOVE, Walter R. , HUGHES, Michael , `Reexamining the ecological fallacy: a study in which aggregate data are critical in investigating the pathological effect of living alone', Social Forces, 57, 1980: 1157-1177. `Social isolation, as measured by living alone, is hypothesized to be a cause of mortality due to suicide and alcoholism. A detailed methodological argument is presented for using aggregate evidence to test this hypothesis.'

274 GREEN, Bryan S.R. , `Social area analysis and structural effects', Sociology, 5, 1971: 1-19. `An attempt is made to identify socially distinct residential areas in an English city along two dimensions, social status and familism. Suggestions are then made for incorporating the area typology into studies of human behavior through the method for separating the effects of social context from the effects of individual attitudes suggested by Davis, Spaeth and Huson.'

275 HERZOG, Allen H. , LEVY, Leo , VERDONK, Ambrose , `Some ecological factors associated with health and social adaptation in the city of Rotterdam', Urban Ecology, 2, 1976: 205-234. `Employing the method of multiple regression, several single equation double-log linear models are estimated to determine the relative importance of certain environmental factors on a number of indices of areal mortality, crime, and social disorganization in 54 municipal areas of the city of Rotterdam.'

276 HORTON, F.E. , REYNOLDS, D.R. , `Effects of urban spatial structure on individual behavior', Economic Geography, 47, 1971: 36-48. `The empirical analysis presented in this paper is focused on the measurement and definition of urban action spaces.'

277 LAFFERTY, William M. , `Industrialization and labour response: notes toward the construction of a multi-level data structure', Acta Sociologica, 13, 1970: 161-189. `The purpose of the paper is twofold; specifically, it presents a theory, model and data-gathering approach for the concrete problem at hand and, generally, it outlines possible theoretical and causal links among three distinct levels of social phenomena.'

278 MELTZER, Leo , SALTER, James , `Organizational structure and the performance and job satisfaction of psychologists', American Sociological Review, 27, 1962: 351-362. `In an attempt to test some aspects of James Worthy's theory of organizational structure, three sets of variables are interrelated: independent, intervening, and dependent variables.'

279 MENZEL, Herbert , KATZ, Elihu , `Social relations and innovation in the medical profession: the epidemiology of a new drug', Public Opinion Quarterly, 19, 1955: 337-352. `This pilot study confirms the role played by face-to-face contacts in mediating influence from the outside world in a case of decision-making among professional experts. Several amendments to the hypothesis of the two-steps-flow of communications became necessary.'

280 NACHMIAS, Chava , `Community and individual ethnicity: the structural context of economic performance', American Journal of Sociology, 85, 1979: 640-659. `The ethnic composition of a community is of greater importance in explaining income and attitude differentials than are the individual's own ethnic attributes.'

281 NIELSEN, François , `The Flemish movement in Belgium after world war II: a dynamic analysis', American Sociological Review, 45, 1980: 76-94. `Predictions of the reactive ethnicity and competition theories are tested using as an indicator of ethnic solidarity the vote for the Flemish movement in Belgium after World War II, measured at the canton level.'

282 ORBELL, J.M. , SHERILL, K.S. , `Racial attitudes and the metropolitan context: a structural analysis', Public Opinion Quarterly, 33, 1969: 46-54.

283 PEARLIN, L.J. , ROSENBERG, Morris , `Nurse-patient social distance and the structural context of a mental hospital', American Sociological Review, 27, 1962: 56-65. `A study of the racial contextual and individual causes of the social distance between nursing staff and patients in a mental hospital.'

284 PENNINGS, Johannes M. , `The relevance of the structural contingency model for organizational effectiveness', Administrative Science Quarterly, 20, 1975: 393-410. `Both subjective and objective data were used to explore the degree of association between measures of structure and of environmental uncertainty and related measures of complexity, resourcefulness, competition and instability. The analysis of the data did not support the model; that is, environment has structural correlates, except for the variables of resourcefulness and complexity.'

285 PHEYSEY, Diana C. , PAYNE, Roy L. , PUGH, Derek S. , `Influence of structure at organizational and group levels', Administrative Science Quarterly, 16, 1971: 61-73. `Groups of line managers and supervisors in two organizations having different organizational structures were compared. As was hypothesized, relationships among the members of the groups in the more mechanistic organization were seen as more formal at all levels of the hierarchy.'

286 PHILLIPSEN, H. , Afwezigheid Wegens Ziekte (Absenteeism through sickness), Groningen, Wolters-Noordhoff, 1969. An investigation into the causes of differences between eighty-five plants in their patterns of absenteeism through sickness.

287 PUGH, Derek S. , HICKSON, D.J. , HINNINGS, C.R. , TURNER, C. , `The context of organization structures', Administrative Science Quarterly, 14, 1969: 91-114. The authors distinguish three levels of behavioural analysis of an organization: (a) organizational structure and functioning, (b) group composition and interaction, (c) individual personality and behaviour.

288 RANSFORD, H. Edward , `Blue collar anger: reactions to student and black protest', American Sociological Review, 37, 1972: 333-346. `A test of the hypothesis that working class respondents are especially antagonistic toward the black and student movements with a sample of white Los Angeles residents. Substantial support for the explanations of blue collar anger is found.'

289 RHODES, A.L. , NAM, Ch.B. , `The religious context of educational expectations', American Sociological Review, 35, 1970: 253-267. `The results of this study are consistent with a theory that the values imported by some religious denominations are more supportive of high levels of educational aspirations than those imported by other denominations.'

290 RICE, Linda E. , MITCHELL, Terence R. , `Structural determinants of individual behavior in organizations', Administrative Science Quarterly, 18, 1973: 56-71. `A new way of looking at organizational structure and its effects on the attitudes and behavior of those within the organization is presented.'

291 RITZEN, Jozef M. , WINKLER, Donald R. , `The revealed preferences of a local government: black/white disparities in scholastic achievement', Journal of Urban Economics, 4, 1977: 310-323. `Many studies of the educational sector implicitly assume schools attempt only to maximize student cognitive achievement subject to a budget constraint. The validity of this assumption is tested in this paper.'

292 ROSENBERG, Morris , `The dissonant religious context and emotional disturbance, American Journal of Sociology, 68, 1962: 1-10. `Data from a sample of high school students suggest that children reared in a dissonant religious context are somewhat more likely to have low selfesteem, to manifest psychosomatic symptoms of anxiety, and to experience depressive affect.'

293 ROUSSEAU, Denise M. , `Characteristics of departments, positions, and individuals: contexts for attitudes and behavior', Administrative Science Quarterly, 23, 1978: 521-540. `This study investigates the relationships of attitudes and behavior to characteristics of departments, positions, and individuals for 271 employees in nineteen departments of two organizations. This study also considers whether job characteristics are potential mediators in these relationships.'

294 SAWYER, Jack , `Dimensions of nations: size, wealth, and politics', American Journal of Sociology, 73, 1964: 145-172. `A total of 236 social, economic, political, and other characteristics were collected from 82 independent nations of more than 800,000 population; 40% of the total variance in the original matrix is accounted for by three dimensions: size, wealth and politics.'

295 SCHMID, Calvin F. , `Urban crime areas: part I', American Sociological Review, 25, 1960: 527-542. The major objective of this paper is to describe in a high degree of specificity the more significant economic, demographic, and social determinants, as well as other dimensions, of crime areas in a large urban community.

296 SILVERMAN, Bernie I. , COCHRANE, Raymond , `Effect of the social context on the principle of belief congruence', Journal of Personality and Social Psychology, 22, 1972: 259-268. The principle of belief congruence is tested. This principle accurately describes the subjects' responses in all social contexts; it describes, however, less accurately the subjects' evaluations; there was a significant relationship between petition signing and discrimination on race, when the hypothetical persons were rated as home purchasers.

297 SLATIN, Gerald T. , `Ecological analysis of delinquency: aggregation effects', American Sociological Review, 34, 1969: 894-906. Aggregated characteristics assessed at a different level of aggregation are studied for their effects on availability of delinquency.

298 BLAU, Zena Smith , `Structural constraints on friendships in old age,' American Sociological Review, 26, 1961: 429-439. An analysis of the influence of friendship relations of older men, without work or widowed. It appears that the number of `equals' in a community is an important factor.

299 VERDONK, Ambrose , Stadsbuurten: de Ene is de Andere Niet (Differences between quarters in a city), Deventer, Van Loghum Slaterus bv, 1979. The author investigates the relationship between city areas and categories of deviants.

300 WEATHERFORD, M. Stephen , `The politics of school busing: contextual effects and community polarization', The Journal of Politics, 42, 1980: 747-765. This paper establishes the existence of a contextual effect on attitudes toward busing and pepares a simple model of the interaction process through which the social environment influences individual attitudes.

301 ZÜNDORF, Lutz , `Zur Erklärung des Vorgesetzten-Untergebenen-Verhaltens in industriellen Organisationen. Eine empirische Kontextanalyse' (Towards an explanation of foreman-worker relations in industrial organizations. An empirical contextual analysis), Soziale Welt, 29, 1978: 87-107.

302 ALKER, Hayward R., jun. , Mathematics and politics, New York/London, Macmillan, 1965: 89-111. The chapter called `Multiple Relationships' contains an outline of some statistical possibilities for relating several variables in the explanation of political processes. The so-called `covariance theorem' is proposed.

303 ALKER, Hayward R., jun. , `The comparison of aggregate and social data: potentialities and problems', Social Science Information, 5, 1966: 63-80. This paper presents a selective range of substantive issues and related quantitative procedures that appear particularly appropriate for aggregate cross-national and cross-cultural analyses.

304 ALKER, Hayward R., jun. , `A typology of ecological fallacies', in: Mattei Dogan and Stein Rokkan (eds), Quantitative ecological analysis in the social sciences, Cambridge, Mass., MIT Press, 1969: 69-86. On the basis of Robinson's classic article on `ecological fallacies', Alker develops a typology of `ecological fallacies' on the basis of mistakes made in covariance decomposition.

305 BARNES, Carl B. , SIMON, Julian L. , `The partial effect of income on suicide is always negative', American Journal of Sociology, 80, 1975: 1454-1460. Linear least-squares regression analysis is used to analyze suicide as a function of income, as well as income and education combined.

306 BLALOCK, Hubert, M., jun. , Causal inferences in nonexperimental research, Chapel Hill, University of North Carolina Press, 1964: 97-114. In the chapter `changes of units of analysis', an attempt to subsume three approaches to the problem of changing units into one model can be found.

307 BLALOCK, Hubert M., jun. , `Aggregation and measurement error', Social Forces, 50, 1971: 151-165. The problem of `ecological correlations' is clarified by the `causal approach to measurement error...but ultimate resolutions will require much better data than are presently available'.

(Reprinted in: Edgar F. Borgatta and David J. Jackson (eds), Aggregate data: analysis and interpretation, Beverly Hills/London, Sage Publications, 1980: 60-79.) `This article discusses three different uses of ratio variables in aggregate data analysis: (1) as measures of theoretical concepts, (2) as a means to control an extraneous factor and (3) as a correction for heteroscedasticity.'

309 BORGATTA, Edgar F. , JACKSON, David J. , `Aggregate data analysis: an overview', Sociological Methods and Research, 7, 1979: 379-383.

310 BOUDON, Raymond, `Propriétés individuelles et propriétés collectives: une problème d'analyse écologique' (Individual properties and collective properties: a problem in ecological analysis), Revue Française de Sociologie, 4, 1964: 275-300. An article about the question of whether or not individual characteristics can be explained by referring to correlations between aggregated data.

311 BOUDON, Raymond, `L' analyse des structures causales: les cas particuliers de l'analyse écologique et de l'analyse contextuelle' (The analysis of causal structures: the particular cases of ecological analysis and contextual analysis), in: Raymond Boudon, L'Analyse Mathématique des Faits Sociaux, Paris, Plon, 1967: 160-201. An analysis of a causal system in which the variables are defined both on the individual and collective level.

312 BOYD, Lawrence H. , IVERSEN, Gudmund K. , Contextual analysis: concepts and statistical techniques, Belmont, Calif., Wadsworth, 1979. A systematic introduction (with computer examples) into different possibilities for contextual analysis.

313 BURSTEIN, Leigh , `Assessing differences between grouped and individual-level regression coefficients: alternative approaches', Sociological Methods and Research, 7, 1978: 5-28. Four techniques for stating the differences between the `least squares estimators' of regression coefficients of groupings of individual data are summarized and evaluated.

314 CARTWRIGHT, Davis S. , `Ecological variables', in: Edgar F. Borgatta (ed.), Sociological methodology, San Francisco, Jossey-Bass, 1969: 155-218. An overview of various meanings of `ecological variable'. Some methodological problems concerning ecological variables are examined.

315 DOREIAN, Patric , `Linear methods with spatially distributed data: spatial disturbances or spatial effects?', Sociological Methods and Research, 9, 1980: 29-60. `This article deals with linear models for which data have been aggregated over well-defined geographic areas.'

316 DUNCAN, Otis D. , DAVIS, Beverly , `An alternative to ecological correlation', American Sociological Review, 18, 1953: 665-666.

317 DUNCAN, Otis D. , CUZZORT, R.P. , DAVIS, Beverly , Statistical geography: problems in analyzing areal data, Glencoe, Ill., Free Press, 1961. An overview of various methods for collecting geographical data and for drawing conclusions from it. The behaviour of correlation and regression coefficients is examined.

318 FIREBAUGH, Glen , `A rule for inferring individual level relationships from aggregate data', American Sociological Review, 43, 1978: 555-572. `Under certain conditions aggregated-level data provide unbiased estimates of individual-level relationships. In this paper these conditions are presented in the form of a single theoretical decision rule: bias is absent when, and only when, the group mean of the independent variable (X) has no effect on Y, with X controlled.'

319 FIREBAUGH, Glen , `Assessing group effects: a comparison of two methods', Sociological Methods and Research, 7, 1979: 384-395. (Reprinted in: Edgar F. Borgatta and David J. Jackson (eds), Aggregate data: analysis and interpretation, Beverly Hills/London, Sage Publications, 1980, 13-24.) `This article examines the relationship between two methods for detecting group effects in nonexperimental data: covariance analysis and contextual analysis. The examination shows that contextual effects are a special case of the group effect obtained in covariance analysis.'

320 GLICK, William , `Problems in cross-level inferences', in: Karlene H. Roberts and Leigh Burstein (eds), Issues in aggregation, San Francisco, Jossey-Bass, 1980: 17-30. `Since the choice of unit influences the relations observed, hypotheses about the determinants of phenomena must explicitly state appropriate unit boundaries.'

321 GOODMAN, Leo A. , `Some alternatives to ecological correlation', American Journal of Sociology, 64, 1959: 610-625. This is an investigation of the conditions under which several methods can be used for the estimation of individual correlations from ecological data.

322 HAMMOND, John L. , `Two sources of error in ecological correlations', American Sociological Review, 38, 1973: 764-777. `Aggregation bias arises when the independent variable has a contextual effect, or when individuals are grouped into neighborhoods on the basis of their similarity on the dependent variable. If aggregation bias is present, no inference about the individual relationship can be drawn from aggregate data.'

323 HANNAN, Michael T. , Aggregation and disaggregation in sociology, Lexington, Mass., D.C. Heath and Company, 1971. (Shortened reprint in: Hubert M. Blalock (ed.), Causal models in the social sciences, New York, Aldine, 1971: 473-507.) This analysis is concerned with the effects of changes in levels of aggregation on parameter estimates in linear causal models. It provides a rather systematic review of the different types of explanation of aggregation bias.

324 HANNAN, Michael T. , BURSTEIN, Leigh , `Estimation from grouped observations', American Sociological Review, 39, 1974: 374-392. `This paper presents a framework for evaluating the conflicting claims in the literature on estimation from grouped observations. Attention is restricted to two-variable substantive models.'

325 HANUSHEK, Eric , JACKSON, John E. , KAIN, J.F. , `Model specification, use of aggregate data, and the ecological correlation fallacy', Political Methodology, 1, 1974: 89-107. An endeavour to clarify the confusing quantity of different reactions to the discovery of the `ecological correlation fallacy'.

326 HYMAN, Martin D. , `Extending the ecological fallacy principle', Sociology and Social Research, 55, 1970: 63-71. `Certain kinds of individual acts can be aggregated into hypothetical as well as concrete collectivities. Some studies present ecological data involving hypothetical collectivities but interpret these data on the individual level. his procedure entails the commission of the ecological fallacy. In the process of demonstrating the above, a more rigorous statement of Robinson's ecological fallacy principle is derived.'

327 IVERSEN, Gudmund R. , `Recovering individual data in the presence of group and individual effects', American Journal of Sociology, 79, 1973: 420-434. `This paper gives some conditions for occasions when individual level data can successfully be recovered from grouped data.'

328 JACKSON, David J. , BORGATTA, Edgar F. , GOLDSMITH, H.F. , `Data analysis in factorial ecology', Sociological Methods and Research, 7, 1979: 356-368. This discussion provides criteria for answering the question `what are the relative merits of common factor analysis and component analysis procedures for factorial ecology research?'

329 LANGBEIN, Laura I. , LICHTMAN, Allan J. , Ecological inference, Beverly Hills/London, Sage Publications, 1978 (series: Quantitative Applications in the Social Sciences, no. 10). In this study a clear overview is given of the `aggregation bias issue'.

330 LINCOLN, James R. , ZEITZ, Gerald , `Organizational properties from aggregate data: separating individual and structural effects', American Sociological Review, 45, 1980: 391-408. The authors `review certain statistical aggregation issues as these pertain to organizational analysis and propose Hauser's path analytic model of analysis of covariance [180] as a device separating individual and structural effects'.

331 MICHELI, Gelberti A. , `Behavior structure and disaggregation; suggestions for a model', Quality and Quantity, 14, 1980: 471-494. `The aim of this paper is to construct a nonlinear model, based on ecological data, concerning the disaggregation of individual behavior.'

(Reprinted in: Edgar F. Borgatta and David J. Jackson, Aggregate data: analysis and interpretation, Beverly Hills/London, Sage Publications, 1980: 131-156.) `The assumption of larger aggregate level coefficients was not consistently upheld.'

333 NATAF, André , `Aggregation' in: D. Sills (ed.), International encyclopedia of the social sciences, Glencoe, Ill., Macmillan/Free Press, 1968: 162-168. An outline of econometric literature on estimators of relation-parameters, computed from aggregated data.

334 OPP, Karl-Dieter, `Das Problem der Dunkelziffer bei der Prüfung von Theorien abweichenden Verhaltens und eine Methode zu ihrer Eliminierung bei ökologischen Untersuchungen' (The problem of data estimation in testing theories of deviant behaviour and a method for eliminating it in ecological investigations), Kölner Zeitschrift für Soziologie und Sozialpsychologie, 21, 1969: 847-63. This article investigates the consequences of unknown figures (`Dunkelziffer') on the validity of theories of deviant behaviour. Furthermore, the possibilities of eliminating that Dunkelziffer are treated.

335 PAPPI, Franz-Urban , `Aggregatdatenanalyse' (Analysis of aggregated data), in: J. van Koolwijk, and M. Wicken-Mayser, Techniken der Empirischen Sozialforschung, Vol. 7, Datenanalyse, München/Wien, Oldenbourg Verlag, 1977: 78-110. This chapter gives an overview of the possibilities of estimating individual parameters from aggregated data.

336 PENDLETON, Brian F. , WARREN, Richard D. , CHANG, H.C. , `Correlated denominators in multiple regression and change analysis', Sociological Methods and Research, 7, 1979: 451-474. This article shows how the interpretation problem `expands from bivariate correlation and regression to partial correlation and multiple regression. Further it gives a review of selected alternative models, focusing on path analysis and the problem of correlated denominators in change and path analyses.'

337 ROBINSON, William S. , `Ecological correlations and the behavior of individuals', American Sociological Review, 15, 1950: 351-357. A classic article which demonstrates that ecological correlation coefficients cannot be translated to the individual level without further information.

338 SCHUESSLER, Karl , `Covariance analysis in sociological research' in: Edgar F. Borgatta (ed.), Sociological methodology, San Francisco, Jossey-Bass, 1968: 219-244. An introduction to covariance analysis as a technique for data analysis is offered, by means of an illustration.

339 SHIVELY, W. Phillips , ` “Ecological inference”: the use of aggregate data to study individuals', American Political Science Review, 63, 1969: 1183-1196. Both the `problem of Robinson' and its solution are discussed. Goodman's version of ecological regression is used as a method to reduce the problem of bias in its estimates.

340 SLATIN, Gerald T. , `A factor analytic comparison of ecological and individual correlations: some methodological implications', The Sociological Quarterly, 15, 1974: 507-520. This paper deals with the ecological fallacy problem on the basis of factor analysis.

341 SMITH, Kent W. , `Another look at the clustering perspective on aggregation problems', Sociological Methods and Research, 5, 1977: 289-316. `The clustering perspective is applied to the analysis of the effects of different types of aggregation, including some not previously discussed, on estimates for models that are correctly specified with homogeneous parameters and for models that are misspecified or have different parametric values for different subsets of the population.'

342 SPRAGUE, John , `Estimating a Boudon-type contextual model: some practical and theoretical problems of measurement', Political Methodology, 3, 1976: 333-353. This paper develops a fragmentary qualitative theory of some determinants of political behaviour. It formalizes the results of that argument in the simplest possible elementary model, and estimates the parameters of the model from observations.

343 STOKES, Donald E. , `A variance components model of political effects' in: John M. Claunch (ed.), Mathematical applications in political science I, Southern Methodist University Press, 1969: 61-85. This paper is an essay on applied mathematics with an emphasis on its subject-matter motivation.

344 STOKES, Donald E. , `Cross-level inference as a game against nature' in: J.L. Bernd (ed.), Mathematical applications in political science IV, University of Virginia Press, 1969: 62-83. A sketch of the evolution of techniques of ecological correlation and regression during a generation, a development of interest in its own right, and a discussion of the hazards by those analysts who attribute to nature to simple a game.

345 WERTS, Charles E. , `Analyzing school effects: Ancova with a fallible covariate', Educational and Psychological Measurement, 31, 1971: 95-104. This paper considers what use might be made of reliability estimates and under what circumstances corrections for unreliability would not decrease the estimated differential school effect.

346 WERTS, Charles E. , LINN, Robert L. , `Considerations when making inferences within analysis of covariance model', Educational Psychological Measurement, 341, 1971: 407-416. It is demonstrated that the conventional methods of multi-level analysis are related to the method of covariance analysis.