PREDICTING PROBABILITY OF ATTRITION ii

PREDICTING

PROBABILITY OF ATTRITION

MODEL SELECTION

Here we have used the backward selection model to select one of the best fit model with significant coefficients.

BACKWARD SELECTION

R Code:

backwd <- step(fullmod, trace=0)

summary(backwd )

Output:

The selected variables in the backward selection model are - Age, Business Travel, Daily Rate, Department, Education Field, Envirinment Satistfaction, Job Involvement, Job Role, Job Level, Job Satistication, Over Time, Stock Option Level, Work Life Balance, Years At Company, Years in Current Role, Years with Current Manager.

Model Validation

Making Prediction

Logistic Regression Model Fit

Model Selection