Header

UZH-Logo

Maintenance Infos

Improving weighted least squares inference


DiCiccio, Cyrus J; Romano, Joseph P; Wolf, Michael (2017). Improving weighted least squares inference. Working paper series / Department of Economics 232, University of Zurich.

Abstract

These days, it is common practice to base inference about the coefficients in a hetoskedastic linear model on the ordinary least squares estimator in conjunction with using heteroskedasticity consistent standard errors. Even when the true form of heteroskedasticity is unknown, heteroskedasticity consistent standard errors can also used to base valid inference on a weighted least squares estimator and using such an estimator can provide large gains in efficiency over the ordinary least squares estimator. However, intervals based on asymptotic approximations with plug-in standard errors often have coverage that is below the nominal level, especially for small sample sizes. Similarly, tests can have null rejection probabilities that are above the nominal level. In this paper, it is shown that under unknown hereroskedasticy, a bootstrap approximation to the sampling distribution of the weighted least squares estimator is valid, which allows for inference with improved finite-sample properties. For testing linear constraints, permutations tests are proposed which are exact when the error distribution is symmetric and is asymptotically valid otherwise. Another concern that has discouraged the use of weighting is that the weighted least squares estimator may be less efficient than the ordinary least squares estimator when the model used to estimate the unknown form of the heteroskedasticity is misspecified. To address this problem, a new estimator is proposed that is asymptotically at least as efficient as both the ordinary and the weighted least squares estimator. Simulation studies demonstrate the attractive finite-sample properties of this new estimator as well as the improvements in performance realized by bootstrap confidence intervals.

Abstract

These days, it is common practice to base inference about the coefficients in a hetoskedastic linear model on the ordinary least squares estimator in conjunction with using heteroskedasticity consistent standard errors. Even when the true form of heteroskedasticity is unknown, heteroskedasticity consistent standard errors can also used to base valid inference on a weighted least squares estimator and using such an estimator can provide large gains in efficiency over the ordinary least squares estimator. However, intervals based on asymptotic approximations with plug-in standard errors often have coverage that is below the nominal level, especially for small sample sizes. Similarly, tests can have null rejection probabilities that are above the nominal level. In this paper, it is shown that under unknown hereroskedasticy, a bootstrap approximation to the sampling distribution of the weighted least squares estimator is valid, which allows for inference with improved finite-sample properties. For testing linear constraints, permutations tests are proposed which are exact when the error distribution is symmetric and is asymptotically valid otherwise. Another concern that has discouraged the use of weighting is that the weighted least squares estimator may be less efficient than the ordinary least squares estimator when the model used to estimate the unknown form of the heteroskedasticity is misspecified. To address this problem, a new estimator is proposed that is asymptotically at least as efficient as both the ordinary and the weighted least squares estimator. Simulation studies demonstrate the attractive finite-sample properties of this new estimator as well as the improvements in performance realized by bootstrap confidence intervals.

Statistics

Downloads

16 downloads since deposited on 10 Aug 2016
16 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Working Paper
Communities & Collections:03 Faculty of Economics > Department of Economics
Working Paper Series > Department of Economics
Dewey Decimal Classification:330 Economics
JEL Classification:C12, C13, C21
Uncontrolled Keywords:Bootstrap, conditional heteroskedasticity, HC standard errors
Language:English
Date:November 2017
Deposited On:10 Aug 2016 12:59
Last Modified:08 Dec 2017 20:09
Series Name:Working paper series / Department of Economics
Number of Pages:43
ISSN:1664-7041
Additional Information:Revised version
Official URL:http://www.econ.uzh.ch/static/wp/econwp232.pdf
Related URLs:http://www.econ.uzh.ch/static/workingpapers.php

Download

Content: Published Version
Filetype: PDF (Version August 2016) - Registered users only
Size: 320kB
Download PDF  'Improving weighted least squares inference'.
Preview
Content: Updated Version
Filetype: PDF (Revised version November 2017)
Size: 290kB