RAND’s recent evaluation attempts to determine the New Leaders principal preparation program’s impact on student test scores, concluding that New Leader principals are slightly more effective, albeit only for certain grade levels, subject areas, and districts. But the study’s overall conclusion is problematic for at least eight reasons. First, the effect sizes are quite small—less than 2 percentile points in the lower grades, where the data allow for more reliable analyses—and the study’s results are more mixed than its bottom-line conclusion would suggest. Indeed, most of the results find no statistically significant impact of New Leader principals on student test scores, and there were nearly as many negative findings as positive ones. Also, the study fails to acknowledge the extant research on the limitations of the study’s value-added model (VAM) with school fixed effects approach. Additionally, problems include a failure to control for the same variables in each VAM, for peer effects, or for the scores of student stayers and leavers. The study also failed to discuss the potential impact of changes in the way student achievement was measured in the districts or to explore how the distribution of school-level scores might have influenced the results. Yet in the face of these problems and limitations, this study implies—incorrectly—that it can offer a valid causal determination that the New Leaders principals had a small positive effect on student test scores.