This paper estimates the effect of privatization on multifactor productivity using comprehensive panel data on initially state-owned manufacturing firms in four economies. We exploit the data's longitudinal dimension to control for preprivatization selection and estimate longrun impacts. The estimates are robust to functional form but sensitive to selection controls. Our preferred random growth estimates imply positive multifactor productivity effects of 15 percent in Romania, 8 percent in Hungary, and 2 percent in Ukraine, but a -3 percent effect in Russia. The foreign privatization effect is larger (18-35 percent) in all countries. Positive domestic effects appear immediately in Hungary, Romania, and Ukraine and continue growing thereafter, but emerge only five years after privatization in Russia. © 2006 by The University of Chicago. All rights reserved.