Model Selection and Regression t-Statistics

ABSTRACT

It is shown that dropping quantitative variables from a linear regression, based on t-statistics, is mathematically equivalent to dropping variables based on commonly used information criteria.

KEYWORDS:

• Information criteria
• Linear regression
• Model selection
• t-Statistics

Acknowledgment

The author thanks Tamara Greasby; our work on her honors thesis at University of Puget Sound explored similar ideas.