Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models
The two-step GMM estimators of Arellano and Bond (1991) and Blundell and Bond (1998) for dynamic panel data models have been widely used in empirical work; however, neither of them performs well in small samples with weak instruments. The continuous-updating GMM estimator proposed by Hansen, Heaton,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-11-01
|
| Series: | Econometrics |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2225-1146/4/4/47 |
| _version_ | 1798002450546819072 |
|---|---|
| author | Richard A. Ashley Xiaojin Sun |
| author_facet | Richard A. Ashley Xiaojin Sun |
| author_sort | Richard A. Ashley |
| collection | DOAJ |
| description | The two-step GMM estimators of Arellano and Bond (1991) and Blundell and Bond (1998) for dynamic panel data models have been widely used in empirical work; however, neither of them performs well in small samples with weak instruments. The continuous-updating GMM estimator proposed by Hansen, Heaton, and Yaron (1996) is in principle able to reduce the small-sample bias, but it involves high-dimensional optimizations when the number of regressors is large. This paper proposes a computationally feasible variation on these standard two-step GMM estimators by applying the idea of continuous-updating to the autoregressive parameter only, given the fact that the absolute value of the autoregressive parameter is less than unity as a necessary requirement for the data-generating process to be stationary. We show that our subset-continuous-updating method does not alter the asymptotic distribution of the two-step GMM estimators, and it therefore retains consistency. Our simulation results indicate that the subset-continuous-updating GMM estimators outperform their standard two-step counterparts in finite samples in terms of the estimation accuracy on the autoregressive parameter and the size of the Sargan-Hansen test. |
| first_indexed | 2024-04-11T11:52:25Z |
| format | Article |
| id | doaj.art-ce25eb7a09c34a13b5d9e612c914978b |
| institution | Directory Open Access Journal |
| issn | 2225-1146 |
| language | English |
| last_indexed | 2024-04-11T11:52:25Z |
| publishDate | 2016-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Econometrics |
| spelling | doaj.art-ce25eb7a09c34a13b5d9e612c914978b2022-12-22T04:25:17ZengMDPI AGEconometrics2225-11462016-11-01444710.3390/econometrics4040047econometrics4040047Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data ModelsRichard A. Ashley0Xiaojin Sun1Department of Economics, Virginia Tech, Blacksburg, VA 24060, USADepartment of Economics and Finance, University of Texas at El Paso, El Paso, TX 79968, USAThe two-step GMM estimators of Arellano and Bond (1991) and Blundell and Bond (1998) for dynamic panel data models have been widely used in empirical work; however, neither of them performs well in small samples with weak instruments. The continuous-updating GMM estimator proposed by Hansen, Heaton, and Yaron (1996) is in principle able to reduce the small-sample bias, but it involves high-dimensional optimizations when the number of regressors is large. This paper proposes a computationally feasible variation on these standard two-step GMM estimators by applying the idea of continuous-updating to the autoregressive parameter only, given the fact that the absolute value of the autoregressive parameter is less than unity as a necessary requirement for the data-generating process to be stationary. We show that our subset-continuous-updating method does not alter the asymptotic distribution of the two-step GMM estimators, and it therefore retains consistency. Our simulation results indicate that the subset-continuous-updating GMM estimators outperform their standard two-step counterparts in finite samples in terms of the estimation accuracy on the autoregressive parameter and the size of the Sargan-Hansen test.http://www.mdpi.com/2225-1146/4/4/47dynamic panel data modelsArellano-Bond GMM estimatorBlundell-Bond GMM estimatorsubset-continuous-updating GMM estimators |
| spellingShingle | Richard A. Ashley Xiaojin Sun Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models Econometrics dynamic panel data models Arellano-Bond GMM estimator Blundell-Bond GMM estimator subset-continuous-updating GMM estimators |
| title | Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models |
| title_full | Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models |
| title_fullStr | Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models |
| title_full_unstemmed | Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models |
| title_short | Subset-Continuous-Updating GMM Estimators for Dynamic Panel Data Models |
| title_sort | subset continuous updating gmm estimators for dynamic panel data models |
| topic | dynamic panel data models Arellano-Bond GMM estimator Blundell-Bond GMM estimator subset-continuous-updating GMM estimators |
| url | http://www.mdpi.com/2225-1146/4/4/47 |
| work_keys_str_mv | AT richardaashley subsetcontinuousupdatinggmmestimatorsfordynamicpaneldatamodels AT xiaojinsun subsetcontinuousupdatinggmmestimatorsfordynamicpaneldatamodels |