Exploiting information from singletons in panel data analysis: A GMM approach

Abstract

We propose a novel procedure, built within a Generalized Method of Moments framework, which exploits unpaired observations (singletons) to increase the efficiency of longitudinal fixed effect estimates. The approach allows increasing estimation efficiency, while properly tackling the bias due to unobserved time-invariant characteristics. We assess its properties by means of Monte Carlo simulations, and apply it to a traditional Total Factor Productivity regression, showing efficiency gains of approximately 8-9 percent. JEL Classification Numbers: C23, C33, C51.

Using information from singletons in fixed-effects estimation: xtfesing

“…The fixed-effects estimator can be obtained as an instrumental variable estimator of (1) with instruments ẍ j,it . The following k moment conditions are therefore satisfied [see (2) in Bruno, Magazzini, and Stampini (2020)]: 2…”

“…The two test statistics are provided with the proposed command. Please refer to Bruno, Magazzini, and Stampini (2020) for details.…”

“…The same equation is estimated using the Bruno, Magazzini, and Stampini (2020) procedure implemented with the command:…”

“…In this article, we describe the xtfesing command, which estimates a static paneldata model with fixed effects and exploits information from the singleton units in the sample with the aim to increase estimation efficiency. The methodology has been proposed by Bruno, Magazzini, and Stampini (2020). The method can also be used to "pool" panel datasets and cross-section observations from other survey waves as in Bruno and Stampini (2009).…”

“…xtfesing implements a two-step generalized method of moments (GMM) estimator (Hansen 1982). Its validity relies on the homogeneity assumption: it requires that the ordinary least-squares (OLS) bias be the same for the panel units and the singletons.…”