Econometricians Have Their Moments: GMM at 32

Abstract

The 2013 Nobel Prize for Economics was awarded to Eugene Fama, Lars Hansen and Robert Shiller for their work on empirical asset pricing. Hansen's primary contribution to the cited work was the development of the generalised method of moments (GMM), a statistical method that has proved such a valuable tool for testing the validity of empirical asset pricing models. The public announcement of the award also acknowledges the wider impact of GMM on empirical analysis in economics and beyond, referring to the 1982 Econometrica paper in which Hansen introduced the method as 'one of the most influential in econometrics'. In this paper, we reflect on how the GMM-based inference framework has evolved since 1982, reviewing developments on four main issues: model diagnostic testing, moment selection, identification and inference in misspecified models. We also illustrate the broader influence of GMM on econometrics by briefly exploring the connections between GMM and three other estimation methods: indirect inference, moment inequality based techniques, and a group of techniques that can be presented equivalently within either the generalised empirical likelihood or info-metric frameworks.

Effects of crime and violence on business confidence: evidence from Rio de Janeiro

“…In order to obtain robust evidence, all specifications will be estimated using different methods: ordinary least squares (OLS), generalized method of moments (GMM) with Newey-West covariance matrix (Newey and West, 1987) and two stages generalized method of moments (GMM-2) with Windmeijer covariance matrix (Windmeijer, 2005). GMM is used to deal with endogeneity and identification problems (Wooldridge, 2001;Hall, 2015). Besides, GMM presents robust estimators even in the presence of serial autocorrelation and heteroskedasticity of unknown form, or nonlinearity, which is typical in macroeconomic time series models (Hansen, 1982) [5].…”

O impacto do gasto discricionário do governo sobre o desacordo de expectativas para a taxa de câmbio: evidências empíricas para uma economia em desenvolvimento

“…Conforme proposto em Dovern et al (2012), a conversão de previsões de eventos fixos em horizonte fixo é realizada aplicando a seguinte fórmula dada pela equação (2): autocorrelação identificados, e a estimativa por GMM-2 utiliza a matriz de Windmeijer (2005) para pequenas amostras. A justificativa para a utilização do GMM se deve a existência de endogeneidade e para captar não-linearidades (Wooldridge, 2001;Hall, 2015). Além disso, o GMM apresenta estimadores robustos mesmo na presença de autocorrelação serial e heteroscedasticidade de forma desconhecida, ou não-linearidade, o que é típico em modelos de séries temporais macroeconômicas (Hansen, 1982).…”

La comunicación fiscal y sus efectos sobre los retornos de los títulos públicos: una aproximación empírica para el caso colombiano

“…Para evaluar las condiciones de sobre identificación necesarias para implementar el método GMM, fue verificado el test J de sobre identificación de Hansen (1983). Los instrumentos fueron seleccionados con base en las sugerencias de Hall (2015). Se consideraron como instrumentos las variables rezagadas de las variables independientes del modelo (2).…”