Selection of variables in linear regression: a pragmatic approach

Abstract

To find the best regression model of p predictor variablesp= l,...k, where k is the number of potential predictor variables, is an important problem. In this paper, we discuss proposals that are easy to implement, accelerate the implicit enumeration algorithms and aid in the selection of variables in linear regression analysis. We illustrate the effectiveness and usefulness of these proposals with an example.

Keywords:

• Subset selection
• implicit enumeration algorithms
• least squares
• minimum sum of absolute errors
• minimum absolute error