iSixSigma

Multicolinearity

Definition of Multicolinearity:

Multicolinearity is the degree of correlation between Xs. It is an important consideration when using multiple regression on data that has been collected without the aid of a design of experiment (DOE). A high degree of multicolinearity produces unacceptable uncertainty (large variance) in regression coefficient estimates. Specifically, the coefficients can change drastically depending on which terms are in or out of the model and also the order they are placed in the model.

Use Ridge Regression or Partial Least Squares (PLS) Regression to get around these problems if DoE is not an option.

« Back to Dictionary Index