The effects of using different data analysis methods on estimates of treatment effects of educational programs were investigated. Various regression models, such as those recommended for Title I program evaluations, were studied. The first effect studied was the amount of bias that might be expected to occur in the various settings. Results indicated that bias was rarely a problem. What did appear to be a problem was the efficiency of the estimates. That is to say that while the estimates were not consistently off of the expected true value (bias), there was considerable inaccuracy in the results (inefficiency). Several recommendations were made with respect to selecting and placing into treatment and control groups. Furthermore, some concern was expressed over the use of the regression model to evaluate educational programs at all. (JKS)