Chapter 20

Dichotomous Predicted Variable

Contents

20.1 Logistic Regression

20.1.1 The Model

20.1.2 Doing It in R and BUGS

20.1.3 Interpreting the Posterior

20.1.4 Perils of Correlated Predictors

20.1.5 When There Are Few 1’s in the Data

20.1.6 Hyperprior Across Regression Coefficients

20.2 Interaction of Predictors in Logistic Regression

20.3 Logistic ANOVA

20.3.1 Within-Subject Designs

20.4 Summary

20.5 R Code

20.5.1 Logistic Regression Code

20.5.2 Logistic ANOVA Code

20.6 Exercises

Fortune and Favor make fickle decrees, it’s

Heads or it’s tails with no middle degrees.

Flippant commandments decreed by law gods, have

Reasons so rare they have minus log odds.

In many situations the value to be predicted is dichotomous (instead of metric). For example, ...

Get Doing Bayesian Data Analysis now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.