TESTING FOR ASSOCIATION IN 2X2 CONTINGENCY-TABLES WITH VERY SMALL SAMPLE SIZES

Applied statistics textbooks generally recommend the use of the chi-square tests of homogeneity and independence with 2 × 2 contingency tables only when the expected frequency of each cell is 5 or more. Recent research has shown this rule-of-thumb criterion to be unnecessarily restrictive, but has not explored the accuracy of the chi-square tests when the total number of observations is less than 20 or when the expected frequencies fall well below one--the primary issues considered in this article. The chi-square tests of homogeneity and independence were found to provide reasonably accurate estimates of Type I error probability for N ≥ 8. Certain alternatives to the chi-square tests are considered. (61 ref) (PsycINFO Database Record (c) 2006 APA, all rights reserved). © 1979 American Psychological Association.