For the latest version of JMP Help, visit JMP.com/help.


Publication date: 04/21/2023

Inverse Prediction

You can use the Logistic platform for inverse prediction, which enables you to make predictions in the opposite direction than usual. Instead of predicting the value of a Y response variable from the value of an X factor variable, inverse prediction is the prediction of the values of an X factor variable from the value of a Y response variable. In logistic regression, instead of a predicting a value of the Y response variable, you predict the probability attributed to each of the levels of the Y response variable. This feature is available only for two-level nominal responses.

The Fit Model platform also has an option that provides an inverse prediction with confidence limits. See “Inverse Prediction” in Fitting Linear Models for more information about inverse prediction.

Note: See also Example of Inverse Prediction.

Want more information? Have questions? Get answers in the JMP User Community (community.jmp.com).