View by Day

Prof. Bo E. Honoré

Princeton University, USA

Authors: Bo E. Honoré and Luojia Hu

The seminar will be based on this paper http://www.princeton.edu/~honore/papers/PoorWomansBootstrap.pdf as well as a follow-up paper (which is in progress).

Here is a combined abstract:   

     The bootstrap is a convenient tool for calculating standard errors of the parameter estimates of complicated econometric models. Unfortunately, the fact that these models are complicated often makes the bootstrap extremely slow or even practically infeasible. This research proposes an alternative to the bootstrap that relies only on the estimation of one-dimensional parameters. We introduce the idea in the context of M- and GMM-estimators. A modification of the approach can be used to estimate the variance of two-step estimators.

We also propose an alternative and simpler method. We compare the two methods in terms of their statistical and practical performance, and we demonstrate their usefulness in Monte Carlo studies and empirical applications.