DOI
10.1177/1536867X20909691
Abstract
In this paper we present ppmlhdfe, a new Stata command for estimation of (pseudo) Poisson regression models with multiple high-dimensional fixed effects (HDFE). Estimation is implemented using a modified version of the iteratively reweighted least-squares (IRLS) algorithm that allows for fast estimation in the presence of HDFE. Because the code is built around the reghdfe package, it has similar syntax, supports many of the same functionalities, and benefits from reghdfe’s fast convergence properties for computing high-dimensional least squares problems. Performance is further enhanced by some new techniques we introduce for accelerating HDFE-IRLS estimation specifically ppmlhdfe also implements a novel and more robust approach to check for the existence of (pseudo) maximum likelihood estimates.
Document Type
Pre-print Article
Publication Date
2020
Publisher Statement
Copyright © 2020 SAGE Publications. Article first published online: March 2020.
DOI: 10.1177/1536867X20909691.
The definitive version is available at: https://journals-sagepub-com.newman.richmond.edu/doi/full/10.1177/1536867X20909691.
Please note that downloads of the article are for private/personal use only.
Full Citation:
Correia, Sergio, Paulo Guimarães, and Tom Zylkin. "Fast Poisson estimation with high-dimensional fixed effects." The Stata Journal 20, no. 1 (2020): 95-115. https://doi-org.newman.richmond.edu/10.1177/1536867X20909691.
Recommended Citation
Correia, Sergio, Paulo Guimarães, and Tom Zylkin. "Fast Poisson estimation with high-dimensional fixed effects." The Stata Journal 20, no. 1 (2020): 95-115. https://doi-org.newman.richmond.edu/10.1177/1536867X20909691.