A stepwise regression technique was used to analyze assessment data while taking differences in nonschool variables across districts into account. The primary purpose of this investigation was to determine whether the inclusion of quadratic and/or interaction terms in a regression model would improve the prediction of school district average score. Results indicated that interaction and quadratic terms improve the prediction of district averages. The second purpose of the investigation was to illustrate certain concepts of regression techniques while attempting to determine the quadratic and/or interaction effects in the regresssion model. (Author)