Bootstrap methods for inference in the Parks model
This paper shows how to bootstrap hypothesis tests in the context of the Parks’s (1967) Feasible Generalized Least Squares estimator. It then demonstrates that the bootstrap outperforms FGLS(Parks)’s top competitor. The FGLS(Parks) estimator has been a workhorse for the analysis of panel data and se...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2020-12-01
|
Series: | Economics: Journal Articles |
Subjects: | |
Online Access: | https://doi.org/10.5018/economics-ejournal.ja.2020-4 |
_version_ | 1811228042585964544 |
---|---|
author | Moundigbaye Mantobaye Messemer Clarisse Parks Richard W. Reed W. Robert |
author_facet | Moundigbaye Mantobaye Messemer Clarisse Parks Richard W. Reed W. Robert |
author_sort | Moundigbaye Mantobaye |
collection | DOAJ |
description | This paper shows how to bootstrap hypothesis tests in the context of the Parks’s (1967) Feasible Generalized Least Squares estimator. It then demonstrates that the bootstrap outperforms FGLS(Parks)’s top competitor. The FGLS(Parks) estimator has been a workhorse for the analysis of panel data and seemingly unrelated regression equation systems because it allows the incorporation of cross-sectional correlation together with heteroskedasticity and serial correlation. Unfortunately, the associated, asymptotic standard error estimates are biased downward, often severely. To address this problem, Beck and Katz (1995) developed an approach that uses the Prais-Winsten estimator together with “panel corrected standard errors” (PCSE). While PCSE produces standard error estimates that are less biased than FGLS(Parks), it forces the user to sacrifice efficiency for accuracy in hypothesis testing. The PCSE approach has been, and continues to be, widely used. This paper develops an alternative: a nonparametric bootstrapping procedure to be used in conjunction with the FGLS(Parks) estimator. We demonstrate its effectiveness using an experimental approach that creates artificial panel datasets modelled after actual panel datasets. Our approach provides a superior alternative to existing estimation options by allowing researchers to retain the efficiency of the FGLS(Parks) estimator while producing more accurate hypothesis test results than the PCSE. |
first_indexed | 2024-04-12T09:51:50Z |
format | Article |
id | doaj.art-2786603510a94b4781134a62a270e3af |
institution | Directory Open Access Journal |
issn | 1864-6042 |
language | English |
last_indexed | 2024-04-12T09:51:50Z |
publishDate | 2020-12-01 |
publisher | De Gruyter |
record_format | Article |
series | Economics: Journal Articles |
spelling | doaj.art-2786603510a94b4781134a62a270e3af2022-12-22T03:37:48ZengDe GruyterEconomics: Journal Articles1864-60422020-12-0114110.5018/economics-ejournal.ja.2020-4Bootstrap methods for inference in the Parks modelMoundigbaye Mantobaye0Messemer Clarisse1Parks Richard W.2Reed W. Robert3Department of Economics and Finance, University of Canterbury, New ZealandBonneville Power Administration, Portland, Oregon, USADepartment of Economics, University of Washington, Washington, USADepartment of Economics and Finance, University of Canterbury, New ZealandThis paper shows how to bootstrap hypothesis tests in the context of the Parks’s (1967) Feasible Generalized Least Squares estimator. It then demonstrates that the bootstrap outperforms FGLS(Parks)’s top competitor. The FGLS(Parks) estimator has been a workhorse for the analysis of panel data and seemingly unrelated regression equation systems because it allows the incorporation of cross-sectional correlation together with heteroskedasticity and serial correlation. Unfortunately, the associated, asymptotic standard error estimates are biased downward, often severely. To address this problem, Beck and Katz (1995) developed an approach that uses the Prais-Winsten estimator together with “panel corrected standard errors” (PCSE). While PCSE produces standard error estimates that are less biased than FGLS(Parks), it forces the user to sacrifice efficiency for accuracy in hypothesis testing. The PCSE approach has been, and continues to be, widely used. This paper develops an alternative: a nonparametric bootstrapping procedure to be used in conjunction with the FGLS(Parks) estimator. We demonstrate its effectiveness using an experimental approach that creates artificial panel datasets modelled after actual panel datasets. Our approach provides a superior alternative to existing estimation options by allowing researchers to retain the efficiency of the FGLS(Parks) estimator while producing more accurate hypothesis test results than the PCSE.https://doi.org/10.5018/economics-ejournal.ja.2020-4parks modelfglspcsesurpanel datacross-sectional correlationbootstrapmonte carlosimulationc13c15c23c33 |
spellingShingle | Moundigbaye Mantobaye Messemer Clarisse Parks Richard W. Reed W. Robert Bootstrap methods for inference in the Parks model Economics: Journal Articles parks model fgls pcse sur panel data cross-sectional correlation bootstrap monte carlo simulation c13 c15 c23 c33 |
title | Bootstrap methods for inference in the Parks model |
title_full | Bootstrap methods for inference in the Parks model |
title_fullStr | Bootstrap methods for inference in the Parks model |
title_full_unstemmed | Bootstrap methods for inference in the Parks model |
title_short | Bootstrap methods for inference in the Parks model |
title_sort | bootstrap methods for inference in the parks model |
topic | parks model fgls pcse sur panel data cross-sectional correlation bootstrap monte carlo simulation c13 c15 c23 c33 |
url | https://doi.org/10.5018/economics-ejournal.ja.2020-4 |
work_keys_str_mv | AT moundigbayemantobaye bootstrapmethodsforinferenceintheparksmodel AT messemerclarisse bootstrapmethodsforinferenceintheparksmodel AT parksrichardw bootstrapmethodsforinferenceintheparksmodel AT reedwrobert bootstrapmethodsforinferenceintheparksmodel |