12.11 WHEN IS MULTICOLLINEARITY NOT A PROBLEM?
Now, depending on the task confronting the analyst, multicollinearity may not in fact present a fatal defect. Weiss1 notes that multicollinearity “does not adversely affect the ability of the sample regression equation to predict the response variable.” He adds that multicollinearity does not significantly affect point estimates of the target variable, confidence intervals for the mean response value, or prediction intervals for a randomly selected response value. However, the data scientist must therefore strictly limit the use of a multicollinear model to estimation and prediction of the target variable. Interpretation of the model would not be appropriate, since the individual coefficients may not make sense, in the presence of multicollinearity. To summarize, models not accounting for multicollinearity may be used for estimation, but not for description or interpretation.