ECON 151 Lecture Notes - Lecture 29: The American Economic Review, Absenteeism, Developing Country
Document Summary
Yi = 0+ 1d+ 2 x+ i where d is the participation in the treatment. D is endogeneous and therefore the structural model is biased. Yet, t is a good instrument for d: Relevance : t is strongly correlated with d. Exogeneity/independence : t is entirely independent from by virtue of randomization. Di = 0 + 1ti + 2 x + which correspond to the estimation of tu and a reduced form: yi = 0+ ittt+ 3x+ which corresponds to the itt estimation. Late can be estimated using an iv model. Reference: vouchers for private schooling in colombia: evidence from a randomized. Natural experiment, j. angrist, eric bettinger, erik bloom, elisabeth king, and michael. Evaluation of a voucher program paces using a rct for secondary school (6th grade). Vouchers cover 50% of the tuition fee: participation among the treated imperfect (never takers) Voucher are distributed to poor primary school who got accepted to a private school.