Second order approximation in a linear regression with heteroskedasticity of unknown form
- 1 January 1996
- journal article
- research article
- Published by Taylor & Francis in Econometric Reviews
- Vol. 15 (1) , 1-32
- https://doi.org/10.1080/07474939608800336
Abstract
We develop stochastic expansions with remainder , where 0<μ<1/2, for a standardised semiparametric GLS estimator, a standard error, and a studentized statistic, in the linear regression model with heteroskedasticity of unknown form. We calculate the second moments of the truncated expansion, and use these approximations to compare two competing estimators and to define a method of bandwidth choice.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Heteroskedasticity and Autocorrelation Consistent Covariance Matrix EstimationEconometrica, 1991
- Asymptotic Normality of Series Estimators for Nonparametric and Semiparametric Regression ModelsEconometrica, 1991
- Hajek Inequalities, Measures of Leverage and the Size of Heteroskedasticity Robust Wald TestsEconometrica, 1989
- The Effect of Estimating Weights in Weighted Least SquaresJournal of the American Statistical Association, 1988
- The Bias of a Heteroskedasticity Consistent Covariance Matrix EstimatorEconometrica, 1987
- Adapting for Heteroscedasticity in Linear ModelsThe Annals of Statistics, 1982
- Local ancillarityBiometrika, 1980
- Evaluation of the Distribution Function of the Two-Stage Least Squares EstimateEconometrica, 1979
- Theoretical StatisticsPublished by Springer Nature ,1974
- Asymptotic Normality and Consistency of the Least Squares Estimators for Families of Linear RegressionsThe Annals of Mathematical Statistics, 1963