Partially adaptive estimation via a normal mixture

Abstract This paper proposes a new partially adaptive regression estimator. The estimator is derived by modeling the disturbance distribution as a variance mixture of normal distributions, yet the true disturbance distribution need not be a variance mixture in order for the proposed estimator to be consistent and asymptotically normal. Moreover, the partially adaptive estimator is shown to be less sensitive to extreme values than the ordinary least-squares estimator, a point that is illustrated with some Monte Carlo experiments. The paper also provides some easily programmed EM algorithms for computing estimates.

[1]  W. Rudin.  Principles of mathematical analysis , 1964 .

[2]  R. Zeckhauser,et al.  Linear Regression with Non-Normal Error Terms , 1970 .

[3]  Benedikt M. Pötscher,et al.  A class of partially adaptive one-step m-estimators for the non-linear regression model with dependent observations , 1986 .

[4]  R. Quandt.  A New Approach to Estimating Switching Regressions , 1972 .

[5]  W. Newey,et al.  Uniform Convergence in Probability and Stochastic Equicontinuity , 1991 .

[6]  Alan B. Forsythe,et al.  Robust Estimation of Straight Line Regression Coefficients by Minimizing pth Power Deviations , 1972 .

[7]  Calyampudi Radhakrishna Rao,et al.  Linear Statistical Inference and its Applications , 1967 .

[8]  R. Jennrich.  Asymptotic Properties of Non-Linear Least Squares Estimators , 1969 .

[9]  H. Kelejian,et al.  The Structure of Simultaneous Equation Estimators: A Generalization towards Nonnormal Disturbances , 1984 .

[10]  Thomas J. Sargent,et al.  Regression With Non-Gaussian Stable Disturbances: Some Sampling Results , 1971 .

[11]  H. White,et al.  A Unified Theory of Consistent Estimation for Parametric Models , 1985, Econometric Theory.

[12]  James B. McDonald,et al.  Partially Adaptive Estimation of Regression Models via the Generalized T Distribution , 1988, Econometric Theory.

[13]  N. Kiefer.  Discrete Parameter Variation: Efficient Estimation of a Switching Regression Model , 1978 .

[14]  Richard J. Butler,et al.  Robust and Partially Adaptive Estimation of Regression Models , 1990 .

[15]  Paul W. Holland,et al.  Two Robust Alternatives to Least-Squares Regression , 1977 .

[16]  H. White.  Asymptotic theory for econometricians , 1985 .

[17]  Boris Gnedenko,et al.  Theory of Probability , 1963 .

[18]  Calyampudi R. Rao,et al.  Linear Statistical Inference and Its Applications. , 1975 .

[19]  Robert F. Phillips.  A constrained maximum-likelihood approach to estimating switching regressions☆ , 1991 .

[20]  M. Aitkin,et al.  Mixture Models, Outliers, and the EM Algorithm , 1980 .

[21]  Richard E. Quandt,et al.  Econometric modelling with non-normal disturbances , 1981 .

[22]  A. Zellner.  Bayesian and Non-Bayesian Analysis of the Regression Model with Multivariate Student- t Error Terms , 1976 .

[23]  J. Elashoff.  A Model for Quadratic Outliers in Linear Regression , 1972 .