On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results
We provide new analytical results for the implementation of the Hausman specification test statistic in a standard panel data model, comparing the version based on the estimators computed from the untransformed random effects model specification under Feasible Generalized Least Squares and the one c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Econometrics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2225-1146/11/4/25 |
| _version_ | 1797381332532199424 |
|---|---|
| author | Julie Le Gallo Marc-Alexandre Sénégas |
| author_facet | Julie Le Gallo Marc-Alexandre Sénégas |
| author_sort | Julie Le Gallo |
| collection | DOAJ |
| description | We provide new analytical results for the implementation of the Hausman specification test statistic in a standard panel data model, comparing the version based on the estimators computed from the untransformed random effects model specification under Feasible Generalized Least Squares and the one computed from the quasi-demeaned model estimated by Ordinary Least Squares. We show that the quasi-demeaned model cannot provide a reliable magnitude when implementing the Hausman test in a finite sample setting, although it is the most common approach used to produce the test statistic in econometric software. The difference between the Hausman statistics computed under the two methods can be substantial and even lead to opposite conclusions for the test of orthogonality between the regressors and the individual-specific effects. Furthermore, this difference remains important even with large cross-sectional dimensions as it mainly depends on the within-between structure of the regressors and on the presence of a significant correlation between the individual effects and the covariates in the data. We propose to supplement the test outcomes that are provided in the main econometric software packages with some metrics to address the issue at hand. |
| first_indexed | 2024-03-08T20:50:52Z |
| format | Article |
| id | doaj.art-89d8cfdc23d5442bbf24fcf6619cdef2 |
| institution | Directory Open Access Journal |
| issn | 2225-1146 |
| language | English |
| last_indexed | 2024-03-08T20:50:52Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Econometrics |
| spelling | doaj.art-89d8cfdc23d5442bbf24fcf6619cdef22023-12-22T14:04:12ZengMDPI AGEconometrics2225-11462023-11-011142510.3390/econometrics11040025On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New ResultsJulie Le Gallo0Marc-Alexandre Sénégas1Center of Economics and Sociology Applied to Rural Areas, UMR1041, l’Institut Agro Dijon, INRAE, University Bourgogne Franche-Comté, 21000 Dijon, FranceBordeaux School of Economics, UMR CNRS6060, University of Bordeaux, 33000 Bordeaux, FranceWe provide new analytical results for the implementation of the Hausman specification test statistic in a standard panel data model, comparing the version based on the estimators computed from the untransformed random effects model specification under Feasible Generalized Least Squares and the one computed from the quasi-demeaned model estimated by Ordinary Least Squares. We show that the quasi-demeaned model cannot provide a reliable magnitude when implementing the Hausman test in a finite sample setting, although it is the most common approach used to produce the test statistic in econometric software. The difference between the Hausman statistics computed under the two methods can be substantial and even lead to opposite conclusions for the test of orthogonality between the regressors and the individual-specific effects. Furthermore, this difference remains important even with large cross-sectional dimensions as it mainly depends on the within-between structure of the regressors and on the presence of a significant correlation between the individual effects and the covariates in the data. We propose to supplement the test outcomes that are provided in the main econometric software packages with some metrics to address the issue at hand.https://www.mdpi.com/2225-1146/11/4/25random effects panel data modelHausman specification testquasi-demeaned model |
| spellingShingle | Julie Le Gallo Marc-Alexandre Sénégas On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results Econometrics random effects panel data model Hausman specification test quasi-demeaned model |
| title | On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results |
| title_full | On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results |
| title_fullStr | On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results |
| title_full_unstemmed | On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results |
| title_short | On the Proper Computation of the Hausman Test Statistic in Standard Linear Panel Data Models: Some Clarifications and New Results |
| title_sort | on the proper computation of the hausman test statistic in standard linear panel data models some clarifications and new results |
| topic | random effects panel data model Hausman specification test quasi-demeaned model |
| url | https://www.mdpi.com/2225-1146/11/4/25 |
| work_keys_str_mv | AT julielegallo onthepropercomputationofthehausmanteststatisticinstandardlinearpaneldatamodelssomeclarificationsandnewresults AT marcalexandresenegas onthepropercomputationofthehausmanteststatisticinstandardlinearpaneldatamodelssomeclarificationsandnewresults |