Root-n-consistent Conditional ML estimation of dynamic panel logit models with fixed effects

TL;DR

This paper introduces new root-n-consistent conditional maximum likelihood estimators for dynamic panel logit models with fixed effects, improving computational efficiency and applicability to various model specifications.

Contribution

The paper develops novel root-n-consistent CMLEs for all parameters, covariate coefficients, and multinomial models, enhancing estimation accuracy and computational simplicity.

Findings

CMLE converges faster than previous methods.

All estimators are asymptotically normally distributed.

Applicable to models with and without covariates.

Abstract

In this paper we first propose a root-n-consistent Conditional Maximum Likelihood (CML) estimator for all the common parameters in the panel logit AR(p) model with strictly exogenous covariates and fixed effects. Our CML estimator (CMLE) converges in probability faster and is more easily computed than the kernel-weighted CMLE of Honor\'e and Kyriazidou (2000). Next, we propose a root-n-consistent CMLE for the coefficients of the exogenous covariates only. We also discuss new CMLEs for the panel logit AR(p) model without covariates. Finally, we propose CMLEs for multinomial dynamic panel logit models with and without covariates. All CMLEs are asymptotically normally distributed.