Bootstrap inference for fixed-effect models
Econometrics
2022-01-28 v1
Abstract
The maximum-likelihood estimator of nonlinear panel data models with fixed effects is consistent but asymptotically-biased under rectangular-array asymptotics. The literature has thus far concentrated its effort on devising methods to correct the maximum-likelihood estimator for its bias as a means to salvage standard inferential procedures. Instead, we show that the parametric bootstrap replicates the distribution of the (uncorrected) maximum-likelihood estimator in large samples. This justifies the use of confidence sets constructed via standard bootstrap percentile methods. No adjustment for the presence of bias needs to be made.
Keywords
Cite
@article{arxiv.2201.11156,
title = {Bootstrap inference for fixed-effect models},
author = {Ayden Higgins and Koen Jochmans},
journal= {arXiv preprint arXiv:2201.11156},
year = {2022}
}