ABSTRACT
Often, a research purpose, question, or hypothesis requires examination of the relationship between a nominal variable and an equal interval variable. Here is an example of a research question that does this:
• Is individual competition for prizes or participation in cooperative learning groups more effective in promoting achievement in first-grade mathematics? (Note: Placement in either an individual competition condition or in a cooperative learning condition is a nominal variable. Mathematics achievement is usually measured with an objective test, which is assumed to be equal interval.)
To examine the relationship between the two variables we are considering, the usual method of analysis is based on a comparison of average group differences. That is, if there is a difference between the averages of the two groups on a mathematics test, then there is a relationship between how they were treated (individual competItIon vs. cooperative learning) and their achievement test scores in mathematics. Example 1 illustrates a proposed method of analysis for this situation. Example 1
Example 1 is based on an experiment with a pretest and a posttest. The relationship between a nominal variable and an equal interval variable can also be examined in a nonexperimental study, as illustrated by this research purpose:
• The purpose of this research is to compare the trust in authority reported by three groups of teenage boys: (1) those who were physically abused, (2) those who were sexually abused, and (3) those who were not abused. Trust in authority will be measured with an objective selfreport measure developed by Doe (2004).
