ABSTRACT
This chapter describes the use of logistic models to estimate probabilities. It introduces models for predicting count data and presents a simple model with one predictor variable where the data are the proportions of trials that display the event. The chapter discusses that the output one typically obtains from running a logistic regression program. It explores how to perform model tests with count data and discusses how logistic models are fitted. The chapter also introduces the important special case in which each observation is a separate trial that either displays the event. It also explores the use of multiple continuous predictors and examines Analysis of variance type models and explains the Analysis of covariance type models. Logistic regression is a method of modeling the relationships between probabilities and predictor variables. The chapter examines regression models for the log-odds of a two-category response variable in which we use more than one predictor variable.
