Regression: Tutorial Introduction

Correlation is a measure of the linear relationship between two variables. The Pearson Product Moment Correlation Coefficient, represented by r, ranges from  +1.00 for a perfect positive relationship to -1.00 for a perfect negative relationship. If there is no linear relationship, r=0. Thus, r indicates both the direction (positive or negative) and the strength of the linear relationship (e.g., weak or strong).

If a relationship is nonlinear, then simple r and regression may not be the appropriate model.

A NOTE ON TERMINOLOGY

Your instructor, textbook, or software package may use different terms than those used in the tutorial. Below we provide a listing of alternate terms.

SS Total: Total variance, SS Corrected Total (SAS)

SS Error: Error variance, Residual variance, SS Residual (SPSS, SYSTAT)

SS Predicted: Explained variance, SS Regression (SPSS, SYSTAT), SS Model (SAS)

R-Squared: Coefficient of Determination

Go to Pre-requisite Questions

1,314 total views, 3 views today