Consistent model and moment selection procedures for GMM estimation with application to dynamic panel data models

Andrews, Donald W.K.; Lu, Bei

doi:10.1016/s0304-4076(00)00077-4

Cited by 708 publications

(469 citation statements)

References 38 publications

Supporting

Mentioning

453

Contrasting

Unclassified

Order By: Relevance

“…As Caner (2009) noticed, models do not need to be nested, but one can rather construct a single large parametric model merging two orthogonal models and let the selection method choose one of the two models. A typical application is structural change models as explained in Andrews and Lu (2001).…”

Section: Introductionmentioning

confidence: 99%

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

Gregorio¹,

Iacus²

2012

Econom. Theory

View full text Add to dashboard Cite

The least absolute shrinkage and selection operator (LASSO) is a widely used statistical methodology for simultaneous estimation and variable selection. It is a shrinkage estimation method that allows one to select parsimonious models. In other words, this method estimates the redundant parameters as zero in the large samples and reduces variance of estimates. In recent years, many authors analyzed this technique from a theoretical and applied point of view. We introduce and study the adaptive LASSO problem for discretely observed multivariate diffusion processes. We prove oracle properties and also derive the asymptotic distribution of the LASSO estimator. This is a nontrivial extension of previous results by Wang and Leng (2007, Journal of the American Statistical Association, 102(479), 1039-1048) on LASSO estimation because of different rates of convergence of the estimators in the drift and diffusion coefficients. We perform simulations and real data analysis to provide some evidence on the applicability of this method.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

Gregorio¹,

Iacus²

2012

Econom. Theory

View full text Add to dashboard Cite

show abstract

“…Prior to the estimation, we have to determine the optimal lag order of the independent variables in the system of equations. We employ the moment selection criteria and downward testing procedures developed by Andrews and Lu (2001). Based on the Hansen test statistics, the optimal lag is found to be one year.…”

Section: Resultsmentioning

confidence: 99%

Determinants of efficiency in the Ghanaian banking industry

Sarpong¹,

Winful²

2017

J. Econ. Int. Finance

View full text Add to dashboard Cite

The twin forces of technological advancement and deregulation have led to financial integration and increased competition in the Ghanaian banking industry. This situation requires an extensive study into efficiency and its determinants in the Ghanaian banking sector, if Ghanaian banks are to survive and compete effectively in the global financial system. This study tries to determine the main determinants of efficiency in the Ghanaian banking industry, using bank specific balanced panel data for 22 banks in Ghana from 2010 to 2016. The study employed Arellano and Bover system generalized method of moment (GMM) estimator to evaluate the determinants of efficiency by regressing micro and macroeconomic variables on two dimensions of bank efficiency: cost and profit efficiency. The results gave an indication that operational cost, credit risk and bank size are the main determinant of cost efficiency in the Ghanaian banking industry; whereas profit efficiency is significantly influenced by only operational cost and credit risk. However, there is weaker evidence on the impact of capital structure, concentration inflation and real gross domestic product (GDP) growth on both cost and profit efficiencies.

show abstract

“…Next, to choose the optimal lag order in both panel VARX specification and moment condition, we use moment and model selection criteria (MMSC) for GMM models based on Hansen [18])'s J-statistic of over-identifying restrictions [3]. Applying MMSC to the GMM estimator, the criteria for selecting lag order is minimizing M-BIC (Bayesian Information Criterion), M-AIC (Akaike's Information Criterion), and M-QIC (Hannan and Quinn Information Criterion).…”

Section: Table2 Unit Root Testsmentioning

confidence: 99%