Performance ratings: accounting for job levels
Now that you're warmed up on logistic regression, you can use it to statistically test what you saw in an earlier graph - are women less likely to be labeled a high performer, even when taking differences in job level into account? You can test this by adding job_level
into the glm()
formula and looking at the new p-value. The process is the same as adding a new variable to a linear regression.
This exercise is part of the course
HR Analytics: Exploring Employee Data in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Run a multiple logistic regression
logistic_multiple <- ___