Estimating Private School Effects for School Children in Peru: Evidence from Individual‐level Panel Data

This paper presents the first value‐added model of private school effects in Peru, using the unique Young Lives longitudinal data. Raw differences in test scores show that children in private schools have higher test scores in both maths and Peabody Picture Vocabulary Test for the most part. Estimates from ordinary least squares regression also indicate the existence of private school premium in maths. However, when we controlled for prior achievement, we find no private school effects in learning. These results hold true for both low‐ability and high‐ability children and are robust to sorting on unobserved ability, grouping on lag structures and transfer between private and public schools.