10.8. Logistic Regression
The discussion of the simple linear regression model in Chapter 9 and the multiple regression models in Sections 10.1–10.7 only considered numerical dependent variables. However, sometimes, the dependent variable is a categorical variable that takes on one of only two possible values. For example, a customer is satisfied or a customer is not satisfied. The use of simple or multiple least-squares regression for a two category response variable (CTQ or Y) often violates the normality assumption and can lead to impossible values of the CTQ (Y).
An alternative approach, logistic regression, originally applied in the health sciences [see Reference 2] enables you to use regression models to predict the probability of a particular ...
Get Statistics for Six Sigma Green Belts with Minitab and JMP now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
