Abstract
Errors of misclassification and their effects on subsequent categorical data analysis are the focus of this paper. The chi-square test for equality of two proportions is examined in the context of errorful categorical data. The effects of such errors on the significance level and power of the test are illustrated. A correction procedure is developed and discussed. The study extends and elaborates upon the existing misclassification literature with a special emphasis on the implications of misclassification errors for educational research with categorical variables.