Title: Estimation of dynastic life-cycle discrete choice models
Authors: Mehmet Soytas - Ozyegin University (Turkey) [presenting]
George-Levi Gayle - Washington University in St Louis (United States)
Limor Golan - Washington University in St Louis (United States)
Abstract: The estimation of a class of life-cycle discrete choice inter-generational models is explored. A new semi-parametric estimator is proposed. It is shown that it is root $N$-consistent and asymptotically normally distributed. We compare our estimator with a modified version of the full solution maximum likelihood estimator (MLE) in a Monte Carlo study. Our estimator performs comparably to the MLE in a finite sample but greatly reduces the computational cost. The quantity-quality trade-offs is shown to depend on the household composition and specialization in the household. Using the proposed estimator, we estimate a dynastic model that rationalizes these observed patterns.