In their review of the current status of graduate training in statistics, methodology, and measurement in psychology, Aiken et al. ( 1990) have assessed the proficiency of graduate students to apply different techniques of statistics in their own research. According to their survey, more than fifty percent of graduate students lacked the competence required to apply basic nonparametric procedures. This section attempts to remedy that state of affairs.
Chapter 11, by Everitt, provides an introduction to the analysis of data collected in the form of count or frequencies. The chapter describes a number of useful methods accompanied by detailed examples that should facilitate comprehension. Readers who need further elaborated expositions of a particular method will find appropriate guidelines in the reference list at the end of the chapter.
One of the most frequently used (and misused) nonparametric procedures in psychology, and the social sciences in general, is the chi-square analysis of contingency tables. The application of that tool is deceptively simple. As early as 1949, D. Lewis and C. J. Burke cited no less than nine common errors made by practicing researchers who employed the chi-square test. Chapter 10, by Delucci, offers an updated review of potential pitfalls when applying the chi-square test and examines supplementary and alternative approaches.
Developments in the analysis of categorical data during the past two decades make an increasing use of log-linear models.