JMP 13 Fitting Linear Models

Introduction to Logistic Models

Logistic regression fits nominal Y responses to a linear model of X terms. To be more precise, it fits probabilities for the response levels using a logistic function. For two response levels, the function is:

where r1 is the first response

or equivalently:

where r1 and r2 are the two responses

Note: When Y is binary and has a nominal modeling type, you can set the Target Level in the Fit Model window to specify the level whose probability you want to model.

For r nominal responses, where , it fits sets of linear ...