This article describes how to go from a Machine Learning, Machine Learning Ensemble, or Regression output model:
To respondent-level variables containing the probabilities of each response based on the Machine Learning model:
- A document containing a Machine Learning, Machine Learning Ensemble, or Regression output created in Displayr.
- Select your Machine Learning model output.
- From the object inspector, click SAVE VARIABLE(S) > Probabilities of Each Response.
A variable set labeled "Probabilities from [modeltype]" is added to the top of your data set.
Technical details: Uses the Probabilities method from the R package flipData. Unlike the defaults in most R packages, this implementation assigns probabilities for observations not in the estimation sample.