Estimating dynamic panel models: Backing out the Nickell bias

We propose a novel estimator for the dynamic panel model, which solves the failure of strict exogeneity by calculating the bias in the first-order conditions as a function of the autoregressive parameter and solving the resulting equation. We show that this estimator performs well as compared with approaches in current use. We also propose a general method for including predetermined variables in fixed-effects panel regressions that appears to perform well.

MoreLess

Year of publication:	2017
Authors:	Hausman, Jerry A. ; Pinkovskiy, Maxim L.
Publisher:	New York, NY : Federal Reserve Bank of New York
Subject:	dynamic panel data \| bias correction \| econometrics

More details

Series:	Staff Report ; 824
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	1002772737 [GVK] hdl:10419/189865 [Handle] RePEc:fip:fednsr:824 [RePEc]
Classification:	C2 - Econometric Methods: Single Equation Models ; C23 - Models with Panel Data ; c26
Source:	EconStor

Persistent link: https://www.econbiz.de/10011942769