The odds ratio is one of the most widely used measures of association for 2 × 2 tables. A generalized Yule coefficient transforms the odds ratio into a correlation-like scale with a range from -1 to 1. Yule's Y, Yule's Q, Digby's H, and a new coefficient are special cases of a generalized Yule coefficient. The new coefficient is shown to be similar in value to the phi coefficient. A confidence interval and sample size formula for a generalized Yule coefficient are proposed. The proposed confidence interval is shown to perform much better than the Wald intervals that are implemented in statistical packages. ata in the form of a 2 × 2 contingency table are common in the social sciences, and many different measures of association for 2 × 2 tables are available (Bishop, Fienberg, and Holland 1975;Reynolds 1977). The phi coefficient is a popular measure of association for 2 × 2 tables and obtains values in the range from -1 to 1 with a value of 0 indicating independence. The phi coefficient is a product-moment correlation between two dichotomous variables. Although the phi coefficient has a clear interpretation, the Wald confidence interval for phi that is used in popular statistical packages can have a coverage probability that is far below the nominal level. The odds ratio is another widely used measure of association for 2 × 2 tables. Unlike the phi coefficient, inferential methods for the odds ratio have excellent small-sample properties, and an exact confidence interval for the odds ratio is available. Edwards (1963) argues that the odds ratio (or a function of the odds ratio) is the only appropriate measure of