This paper describes the historical development of analytic techniques for frequency data presented as 2 x 1 or 2 x 2 contingency tables. The issues raised include: the need for a continuity correction when estimating the exceedance probability of a discrete statistic; the vulnerability of such statistics to a conservative bias when used in hypothesis testing; and the different statistical models that may underlie contingency tables. In the case of 2 x 1 contingency tables the recommended technique is the binomial test with a modified decision procedure for hypothesis testing. In the case of 2 x 2 contingency tables there is a single statistic approximating the chi-square distribution which can be used to test the hypothesis of an association between the two relevant variables and which in most practical situations is robust with respect to the occurrence of small expected cell frequencies.
Get full access to this article
View all access options for this article.
References
1.
Kempthorne O.In dispraise of the exact test: Reactions. Journal of Statistical Planning and Inference1979; 3: 199-213.
2.
Pearson K.On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Philosophical Magazine1900; Series 5, 50: 157-75.
3.
Greenwood, M. Jr, Yule GUThe statistics of anti-typhoid and anti-cholera inoculations and the interpretation of such statistics in general. Proceedings of the Royal Society of Medicine: Section on Epidemiology and State Medicine1915; 8: 113-94.
4.
Fisher RAOn the interpretation of χ2 from contingency tables and the calculation of P. Journal of the Royal Statistical Society1922; 85: 87-94.
5.
Cochran WGThe χ2 test of goodness of fit. Annals of Mathematical Statistics1952; 23: 315-45.
6.
Fienberg SEFisher's contributions to the analysis of categorical data. In Fienberg SE, Hinkley DV eds, R.A. Fisher: An appreciation. New York: Springer-Verlag, 1980: 75-84.
7.
Fisher RAStatistical methods for research workers, 1st ed. Edinburgh: Oliver and Boyd, 1925.
8.
Croxton FEElementary statistics with applications in medicine and the biological sciences . New York: Dover, 1953.
9.
Ferguson GA, Takane Y.Statistical analysis in psychology and education, 6th ed. New York: McGraw-Hill, 1989.
Kendall MG, Stuart A. (1967). The advanced theory of statistics, Vol. 2, 2nd ed. London : Griffin, 1967.
12.
Wilks SSThe likelihood test of independence in contingency tables. Annals of Mathematical Statistics1935; 6: 190-96.
13.
Kullback S.Information theory and statistics. New York: Wiley, 1959.
14.
Akaike H.Information theory and an extension of the maximum likelihood principle. In Petrov BN, Csaki F eds, Second international symposium on information theory. Budapest: Akademiai Kiado , 1973: 267-81.
15.
Sakamoto Y., Ishiguro M., Kitagawa G.Akaike information criterion statistics. Dordrecht: Reidel, 1986.
16.
Bulmer MGPrinciples of statistics, 2nd ed. Edinburgh: Oliver and Boyd, 1967 .
17.
Barnard GASignificance tests for 2 x 2 tables. Biometrika1947; 34: 123-38.
18.
Pearson ESThe choice of statistical tests illustrated on the interpretation of data classed in a 2 x 2 table. Biometrika1947; 34: 139-67.
19.
Rhoades HM, Overall JEA sample size correction for Pearson chi-square in 2 x 2 contingency tables. PsychologicalBulletin1982; 91: 418-23.
20.
Upton Gjg.Cross-classified data. In Lovie AD ed. New developments in statistics for psychology and the social sciences . London: The British Psychological Society and Methuen, 1986: 70-92.
21.
Fisher RAThe design of experiments. Edinburgh: Oliver and Boyd, 1935.
22.
Gridgeman NTThe lady tasting tea and allied topics. Journal of the American Statistical Association1959; 54: 776-83.
23.
Holschuh N.Randomization and design: 1. In Fienberg SE , Hinkley DV eds, R.A. Fisher: An appreciation. New York : Springer-Verlag, 1980: 35-45.
24.
Phillips DSBasic statistics for health science students. San Francisco : WH Freeman, 1978.
25.
Siegel S.Nonparametric statistics for the behavioral sciences. New York: McGraw-Hill, 1956.
26.
Haviland MGYates's correction for continuity and the analysis of 2 x 2 contingency tables. Statistics in Medicine1990; 9: 363-67.
27.
Kendall MG, Buckland WRA dictionary of statistical terms, 3rd ed. Edinburgh: Oliver and Boyd, 1971 .
28.
Yates F.Contingency tables involving small numbers and the χ2 test. Journal of the Royal Statistical Society1934; Suppl. 1: 217-35.
29.
Fisher RAStatistical methods for research workers, 5th ed. Edinburgh: Oliver and Boyd, 1934.
30.
Irwin JOTests of significance for differences between percentages based on small numbers . Metron1935; 12: 83-94.
31.
Rohatgi VKStatistical inference. New York: Wiley, 1984.
32.
Basu D.Discussion of Joseph Berkson's paper 'In dispraise of the exact test'. Journal of Statistical Planning and Inference1979; 3: 189-92.
33.
Richardson Jte.Variants of chi-square for 2 x 2 contingency tables. British Journal of Mathematical and Statistical Psychology1990; 43: 309-26.
Conover WJSome reasons for not using the Yates continuity correction on 2 x 2 contingency tables. Journal of the American Statistical Association1974; 69: 374-76.
36.
Haber, M.A comparison of some continuity corrections for the chi-squared test on 2 x 2 tables. Journal of the American Statistical Association1980; 75: 510-15.
37.
Lawal HB, Upton Gjg.On the use of X2 as a test of independence in contingency tables with small cell expectations. Australian Journal of Statistics1984; 26: 75-85.
38.
Mantel N., Greenhouse SWWhat is the continuity correction?The American Statistician1968; 22(5): 27-30.
39.
Maxwell EAAnalysis of contingency tables and further reasons for not using Yates correction in 2 x 2 tables. Canadian Journal of Statistics1976; 4: 277-90.
40.
Camilli G., Hopkins KDApplicability of chi-square to 2 x 2 contingency tables with small expected cell frequencies. PsychologicalBulletin1978 ; 85: 163-67.
41.
Yates F.Tests of significance for 2 x 2 contingency tables. Journal of the Royal Statistical Society Series A 1984; 147: 426-63.
42.
Lewith GT, Machin D.A randomised trial to evaluate the effect of infra-red stimulation of local trigger points, versus placebo, on the pain caused by cervical osteoarthrosis . International Journal of Acupuncture and Electro-Therapeutic Research1981; 6: 277-84.
43.
Daly LE, Bourke GJ, McGilvray J.Interpretation and uses of medical statistics, 4th ed. Oxford: Blackwell, 1991.
44.
Fisher RAThe logic of inductive inference. Journal of the Royal Statistical Society1935; 98: 39-82.
45.
Fisher RAThe interpretation of experimental four-fold tables. Science1941; 94: 210-11.
46.
Berkson J.In dispraise of the exact test: Do the marginal totals of the 2 x 2 table contain relevant information respecting the table proportions? Journal of statistical Planning and Inference1978; 2: 27-42.
47.
Barnard GAA new test for 2 x 2 tables. Nature1945;156: 177.
48.
Fisher RAStatistical methods and scientific inference. Edinburgh : Oliver and Boyd, 1956.
49.
Fisher RAA new test for 2 x 2 tables. Nature1945; 156: 388.
50.
Berkson J.Do the marginal totals of the 2 x 2 table contain relevant information respecting the table proportions? Journal of Statistical Planning and Inference1978; 2: 43-44.
51.
Camilli G.The test for homogeneity for 2 x 2 contingency tables: A review of and some personal opinions on the controversy. Psychological Bulletin1990; 108: 135-45.
52.
Fisher RAThe logical inversion of the notion of the random variable. Sankhyä1945; 7: 129-32.
53.
Barnard GAStatistical inference. Journal of the Royal Statistical Society Series B 1949; 11: 115-49.
54.
Barnard GADiscussion of Dr Yates's paper. Journal of the Royal Statistical Society Series A 1984; 147:449-50.
55.
Upton Gjg.Fisher's exact test. Journal of the Royal Statistical Society Series A 1992 ; 155: 395-402.
56.
Haber M.Comments on 'The test of homogeneity for 2 x 2 contingency tables: A review of and some personal opinions on the controversy' by G Camilli. PsychologicalBulletin1990; 108: 146-49.
57.
Plackett RLThe continuity correction in 2 x 2 tables. Biometrika1964; 51: 327-37.
58.
Haber M.An exact unconditional test for the 2 x 2 comparative trial. Psychological Bulletin1986; 99: 129-32.
59.
Barnard GA2 x 2 tables: A note on ES Pearson's paper. Biometrika1947; 34: 168-69.
60.
Kendall MG, Stuart A.The advanced theory of statistics, Vol. 1, 2nd ed. London: Griffin , 1963.
61.
Patnaik PBThe power function of the test for the difference between two proportions in a 2 x 2 table. Biometrika1948; 35: 157-75.
62.
Upton Gjg.A comparison of alternative tests for the 2 x 2 comparative trial. Journal of the Royal Statistical Society Series A 1982; 145: 86-105.
63.
Haldane Jbs.The mean and variance of χ2, when used as a test of homogeneity, when expectations are small. Biometrika1939; 31: 346-55.
64.
Garside GR, Mack C.Actual Type I error probabilities for various tests in the homogeneity case of the 2 x 2 contingency table. The American Statistician1976; 30: 18-21.
65.
D'Agostino RB, Chase W., Belanger A.The appropriateness of some common procedures for testing the equality of two independent binomial populations. The American Statistician1988; 42: 198-202.
66.
Haber M.The continuity correction and statistical testing. International Statistical Review1982; 50: 135-44.
67.
Liddell D.Practical tests of 2 x 2 contingency tables. The Statistician1976; 25: 295-304.
68.
Overall JEContinuity correction for Fisher's exact probability test. Journal of Educational Statistics1980; 5: 177-90.
69.
Overall JE, Rhoades HM, Starbuck RRSmall-sample tests for homogeneity of response probabilities in 2 x 2 contingency tables. PsychologicalBulletin1987; 102: 307-14.
70.
Overall JE, Starbuck RRF-test alternatives to Fisher's exact test and to the chi-square test of homogeneity in 2 x 2 tables. Journal of Educational Statistics1983; 8: 59-73.
71.
D'Agostino RB, Chase W., Belanger A.The appropriateness of some common procedures for testing the equality of two independent binomical populations. The American Statistician1988; 42: 198-202.
72.
Camilli G., Hopkins KDTesting for association in 2 x 2 contingency tables with very small sample sizes. Psychological Bulletin1979; 86: 1011-14.
73.
Grizzle JEContinuity correction in the χ2-test for 2 x 2 tables. The American Statistician1967; 21(4): 28-32.
74.
Roscoe JT, Byars JAAn investigation of the restraints with respect to sample size commonly imposed on the use of the chi-square statistic. Journal of the American Statistical Association1971; 66: 755-59.
75.
Starmer CF, Grizzle JE, Sen PKComment. Journal of theAmerican Statistical Association1974;69:376-78.
76.
Streitberg B., Roehmel J.Alternatives to Fisher's exact test? Biometrie und Informatik in Medizin und Biologie1991; 22: 139-46.
77.
Cox DR, Snell EJAnalysis of binary data, 2nd ed. London: Chapman and Hall, 1989.
78.
Bradley DR, Bradley TD, McGrath SG, Cutcomb SDType I error rate of the chi-square test of independence in R x C tables that have small expected frequencies. Psychological Bulletin1979; 86: 1290-97.
79.
Holland WW, Bailey P., Bland JMLong-term consequences of respiratory disease in infancy. Journal of Epidemiology and Community Health1978;32:256-59.
80.
Centerwall BS, Armstrong CW, Funkhouser LS, Elzay RPErosion of dental enamel among competitive swimmers at a gas-chlorinated swimming pool. American Journal of Epidemiology1986;123: 641-47.
Siegel S., Castellan NJ Jr.Nonparametric statistics for the behavioral sciences, 2nd ed. New York: McGraw-Hill , 1988.
85.
Kendall MG, Stuart A.The advanced theory of statistics, Vol. 2, 4th ed. London: Griffin , 1979.
86.
Mantel N.Comment and a suggestion. Journal of the American Statistical Association1974; 69: 378-80.
87.
Mantel N.The continuity correction. The American Statistician1976; 30: 103-104.
88.
Tocher KDExtension of the Neyman-Pearson theory of tests to discontinuous variates . Biometrika1950; 37: 130-44.
89.
Lewis D., Burke CJThe use and misuse of the chi-square test. Psychological Bulletin1949; 46: 433-89.
90.
Hays WLStatistics. New York: Holt, Rinehart and Winston, 1963.
91.
Overall JEComment. Statistics in Medicine1990; 9:379-82.
92.
Corsten Lca , de Kroon Jpm.Comment on J Berkson's paper `In dispraise of the exact test'. Journal of Statistical Planning and Inference1979; 3: 193-97.
93.
Bradley DR, Seely DLEmpirical determination of the power of the chi-square test of independence in 2 x 2 tables. Proceedings of the Statistical Computing Section of the American Statistical Association1977; 138-44.
94.
Comrey ALA first course in factor analysis. New York: Academic Press, 1973.
95.
Mehta CR, Hilton JFExact power of conditional and unconditional tests: Going beyond the 2 x 2 contingency table. The American Statistician1993; 47: 91-98.
96.
Overall JEPower of chi-square tests for 2 x 2 contingency tables with small expected frequencies. Psychological Bulletin1980; 87: 132-35.
