Maximum Likelihood Estimation of Misspecified Models

Twenty Years Later

T. Fomby|R. Carter Hill

Emerald

This book can be opened with

Hardback

9780762310753

12 December 2003

$167.99

Description
Contents

This volume is the result of an "Advances in Econometrics" conference held in November of 2002 at Louisiana State University in recognition of Halbert White's pioneering work published in Econometrica in 1980 and 1982 on robust variance-covariance estimation and quasi-maximum likelihood estimation. It contains 11 papers on a range of related topics including the estimation of possibly misspecified error component and fixed effects panel models, estimation and inference in possibly misspecified quantile regression models, quasi-maximum likelihood estimation of linear regression models with bounded and symmetric errors and quasi-maximum likelihood estimation of models with parameter dependencies between the mean vector and error variance-covariance matrix. Other topics include GMM, HAC, Heckit, asymmetric GARCH, Cross-Entropy, and multivariate deterministic trend estimation and testing under various possible misspecifications.

A comparative study of pure and pretest estimators for a possibly misspecified two-way error component model (B.H. Baltagi, G. Bresson, A. Pirotte). Tests of common deterministic trend slopes applied to quarterly global temperature data (T.B. Fomby, T.J. Vogelsang). The sandwich estimate of variance (J.W. Hardin). Test statistics and critical values in selectivity models (R.C. Hill, L.C. Adkins, K.A. Bender). Estimation, inference, and specification testing for possibly misspecified quantile regression (T.-H. Kim, H. White). Maximum likelihood estimation with bounded symmetric errors (D. Miller, J. Eales, P. Preckel). Consistent quasi-maximum likelihood estimation with limited information (D. Miller, S.-H. Lee). An examination of the sign and volatility switching ARCH models under alternative distributional assumptions (M.F. Omran, F. Avram). Estimating a linear exponential density when the weighting matrix and mean parameter vector are functionally related (C.-Y. Sin). Testing in GMM models without truncation (T.J. Vogelsang). Bayesian analysis of misspecified models with fixed effects (T. Woutersen).