Debiased Inference of Average Partial Effects in Single-Index Models
Statistics Theory
2018-11-07 v1 Statistics Theory
Abstract
We propose a method for average partial effect estimation in high-dimensional single-index models that is root-n-consistent and asymptotically unbiased given sparsity assumptions on the underlying regression model. This note was prepared as a comment on Wooldridge and Zhu [2018], forthcoming in the Journal of Business and Economic Statistics.
Cite
@article{arxiv.1811.02547,
title = {Debiased Inference of Average Partial Effects in Single-Index Models},
author = {David A. Hirshberg and Stefan Wager},
journal= {arXiv preprint arXiv:1811.02547},
year = {2018}
}