DM Stat-1 Articles
Link to Home

Link to Articles

Link to Consulting

Link to Seminar

Link to Stat-Chat

Link to Software

Link to Clients

The Importance of the Regression Coefficient
Bruce Ratner, Ph.D.

Interpretation of the ordinary regression model - the most popular technique for making predictions of a single continuous variable - focuses on the model's coefficients with the aid of three concepts: the statistical p-value, variables "held constant," and the standardized regression coefficient. The purpose of this article is to take a closer look at these widely used, yet often misinterpreted concepts. This article demonstrates that the statistical p-value as a sole measure for declaring Xi an important predictor is sometimes problematic; secondly, that the concept of variables "held constant" is critical for reliable assessment of how Xi affects the prediction of Y; and lastly, that the standardized regression coefficient provides the correct ranking of variables in order of predictive importance under special circumstances.

For more information about this article, call Bruce Ratner at 516.791.3544,
1 800 DM STAT-1, or e-mail at