The accuracy with which regression models estimate treatment effects is dependent upon a number of conditions. The stability of the regression line (a function of sample size and correlation between pretest and posttest) is said to be the most important of these conditions. The utility of regression models is proportional to the size of the correlation between pretest and posttest. As the size of the correlation increases, the predicted posttest scores of the treatment group decreases. This produces a corresponding increase in the difference between predicted and observed scores. It is further stated that in compensatory education projects, factors which lower the correlation between pretest and posttest for low scoring students may invalidate the results. Given these condition, this study examined the impact of the correlation between pretest and posttest on the accuracy with which regression models estimate treatment effects in Title I evaluation. More specifically, the effect of the correlation between pretest and posttest on the estimation of treatment effects with regression models was studied, using simulated data. Conclusions regarding the importance of the pretest-posttest correlation varied, depending on whether more emphasis is placed upon unbiased estimates or efficiency. (Author/JKS)