To assess the degree of association extant in an r × c contingency table, analysts are likely to use two compound least-squares measures, Crameér's or Light and Margolin's Sample specific by, definition, both coefficients are positively biased. To estimate the degree to which two nominally scaled variables are related in a population, simple adjustments to reduce this bias can and should be made when the sample size is not large. Accordingly, the adjusted coefficients and are proposed. As shown, these generalized second-moment chance-corrected measures correspond with their multiple regression and point multiserial correlation counterparts, and
Get full access to this article
View all access options for this article.
References
1.
AcockA. C.StavigG. R. (1979). A measure of association for nonparametric statistics. Social Forces, 57, 1381–1386.
2.
AndersonR. J.LandisJ. R. (1980). CATANOVA for multidimensional tables: Nominal-scale response. Communications in Statistics, A9, 1191–1206.
3.
AndrewsF. M.MessengerR. C. (1973). Multivariate nominal scale analysis. Ann Arbor, Michigan: Institute for Social Research.
4.
ArmitageP. (1955). Tests for linear trends in proportions and frequencies. Biometrics, 11, 375–386.
5.
BartlettM. S. (1939). A note on tests of significance in multivariate analysis. Proceedings of the Cambridge Philosophical Society, 35, 180–185.
6.
BlalockH. M. (1958). Probabilistic interpretations for the mean square contingency. Journal of the American Statistical Association, 53, 102–105.
7.
City of New York. Department of Health (1983). Acquired immune deficiency syndrome (AIDS): Update. City Health Information. 2 February 1983.
8.
CohenJ. (1982). Set correlation as a general multivariate data-analytic method. Multivariate Behavioral Research, 17, 301–341.
9.
CramerE. M.NicewanderW. A. (1979). Some symmetric, invariant measures of multivariate association. Psychometrika, 44, 43–54.
10.
CramérH. (1946). Mathematical methods of statistics. Princeton, NJ: Princeton University Press.
11.
CuretonE. (1966). On correlation coefficients. Psychometrika, 31, 605–607.
12.
DanielW. W. (1978). Applied nonparametric statistics. Boston: Houghton Mifflin.
13.
EzekielM. (1930). Methods of correlational analysis. New York: John Wiley & Sons.
14.
FisherR. A. (1922a). On the significance of χ2 from contingency tables, and on the calculation of P. Journal of the Royal Statistical Society, 85, 87–91.
15.
FisherR. A. (1922b). The goodness of fit of regression formulae, and the distribution of regression coefficients. Journal of the Royal Statistical Society, 85, 597–612.
16.
FisherR. A. (1924a). On a distribution yielding the error functions of several well known statistics. Proceedings of the International Mathematical Congress, Toronto, 805–813. (Published 1928.)
17.
FisherR. A. (1924b). The influence of rainfall on the yield of wheat at Rothamstead. Philosophical transactions of the Royal Society of London, Series B, 213, 89–142.
18.
FisherR. A. (1925). Statistical methods for research workers. London: Oliver & Boyd.
19.
GearyR. C. (1927). Some properties of correlation and regression in a limited universe. Metron, 7, 83–119.
20.
GearyR. C. (1940). The mathematical expectation of the mean square contingency when the attributes are mutually independent. Journal of the Royal Statistical Society, 103, 90–91.
21.
GoodmanL. A.KruskalW. H. (1954). Measures of association for cross classifications. Journal of the American Statistical Association, 49, 732–764.
22.
HaysW. L. (1963). Statistics for psychologists. New York: Holt, Reinhart & Winston.
23.
HirschfeldH. O. (1935). A connection between correlation and contingency. Proceedings of the Cambridge Philosophical Society, 31, 520–524.
24.
HooperJ. W. (1959). Simultaneous equations and canonical correlation theory. Econometrika, 27, 245–256.
25.
KelleyT. L. (1935). An unbiased correlation measure. Proceedings of the National Academy of Sciences, 21, 554–559.
26.
KruskalW. H.WallisW. A. (1952). Use of ranks in one-criterion variance analysis. Journal of the American Statistical Association, 47, 583–621.
27.
LexisW. (1877). Zur Theorie der Massenerscheinungen in der menschlichen Gesellschaft. Freiberg: Friedrich Wagner.
28.
LightR. J.MargolinB. H. (1971). An analysis of variance for categorical data. Journal of the American Statistical Association, 66, 534–544.
29.
MaungK. (1942). Measurement of association in a contingency table with special reference to the pigmentation of hair and eye colours of Scottish school children. Annals of Eugenics, 11, 189–223.
30.
MuellerJ. H.SchueslerK. F.CostnerH. L. (1970). Statistical reasoning in sociology (2nd ed.). New York: Houghton Mifflin.
31.
OlivieroA. F. (1973). Children's evaluations of family roles: A cross cultural comparison. International Journal of Psychology, 8, 153–158.
32.
PearsonK. (1903). Mathematical contributions to the theory of evolution. On homotyposis in homologous but differentiated organs. Proceedings of the Royal Society, Series A, 71, 288–313.
33.
PearsonK. (1904). Mathematical contributions to the theory of evolution. XIII. On the theory of contingency and its relation to association and normal correlation. Drapers' Company Research Memoirs, Biometric Series 1.
34.
PearsonK. (1905). Mathematical contributions to the theory of evolution. XIV. On the general theory of skew correlation and non-linear regression. Drapers' Company Research Memoirs, Biometric Series II.
35.
PearsonK. (1911a). The grammar of science. (3rd ed.). London: Adam and Charles Black.
36.
PearsonK. (1911b). On a correction to be made to the correlation ratio η. Biometrika, 8, 254–256.
37.
PearsonK. (1914). On an extension of the method of correlation by grades or ranks. Biometrika, 10, 416–418.
38.
PearsonK. (1923). On the correction necessary for the correlation ratio η. Biometrika, 14, 412–417.
39.
PearsonK. (Unsigned). (1929). Tables for ascertaining the significance or non-significance of association measured by the correlation ratio. (Introduction to tables for η2 computed by Dr. T. L. Woo.). Biometrika, 21, 1–8.
40.
PearsonK.HeronD. (1913). On theories of association. Biometrika, 9, 159–315.
41.
RietzH. L. (1932). On the Lexis theory and the analysis of variance. Bulletin of the American Mathematical Society, 38, 731–735.
42.
SakodaJ. M. (1977). Measures of association for multivariate contingency tables. Proceedings of the Social Statistics Section of the American Statistical Association (Part II), 777–780.
43.
SärndalC. E. (1974). A comparative study of association measures, Psychometrika, 39, 165–187.
44.
SerlinR. C. (1982). A multivariate measure of association based on the Pillai-Bartlett procedure. Psychological Bulletin, 91, 413–417.
45.
SouthwoodK. E. (1974). Goodman and Kruskal's tau-b as correlation ratio. Sociological Methods & Research, 3, 82–110.
46.
StewartD.LoveW. (1968). A general canonical correlation index. Psychological Bulletin, 70, 160–163.
47.
TschuprowA. A. (1925). Grundbegriffe und Grundprobleme der Korrelationstheorie. Leipzig: B. G. Teubner.
48.
WeilerH. (1966). A coefficient measuring the goodness of fit. Technometrics, 8, 327–334.
49.
WelchB. L. (1938). On tests for homogeneity. Biometrika, 30, 149–158.
50.
WelkowitzJ.EwenR. B.CohenJ. (1976). Introductory statistics for the behavioral sciences (2nd ed.). New York: Academic Press.
51.
WilliamsE. J. (1952). Use of scores for the analysis of association in contingency tables. Biometrika, 39, 274–289.
52.
YuleG. U. (1907). On the theory of correlation for any number of variables, treated by a new system of notation. Proceedings of the Royal Society, Series A, 79, 182–193.
