Abstract: | We recommend use of the widely available computer package GLIM to analyze relationships involving categorical, or qualitative, variables. The package is flexible and fairly simple to use and readily produces data plots as well as information on parameter estimates and residual values. In order to explain how to fit log-linear and logistic-linear models using GLIM, we give two examples based on sample survey data from grocery shoppers in Oxford, England. In the first, we examine relationships between a categorical response to an attitude statement and categorical explanatory variables using the log-linear model and, in the second, relationships between use and a mixture of continuous and categorical explanatory variables using the logistic-linear (logit) model. |