Exclusive Content & Downloads from ASQ

Some Thoughts on Variable-Selection in Multiple Regression

Summary: The practice of variable-selection in multiple linear regression is examined both logically and statistically in terms of the major objectives of regression analysis. It is argued that in addition to goodness-of-fit considerations, due attention should be given to determining the domain, in the space of regressors, in which the regression equation can be used as a prediction device. Such a domain has been called the "effective prediction domain" (EPD). It is shown that failure to do so can result in serious misuse of the regression equation, especially when regressors have been omitted.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

Subscribe to Journal of Quality Technology

Access this and ALL OTHER Journal of Quality Technology online articles. You'll also receive the print version by mail.

  • Topics: Process Capability
  • Keywords: Process capability (Cp),Goodness of fit,Multiple regression,Prediction,Selection,Collinearity,Regression
  • Author: Mandel, John
  • Journal: Journal of Quality Technology