Abstract
Reliable statistical inference in fixed-effects panel models depends on accurate covariance matrix estimation, particularly in short panels affected by serial correlation and heteroskedasticity. This study proposes the Fixed Effects Adaptive Robust Shrinkage Covariance (FE-ARSC) estimator, a covariance estimation approach designed to improve finite-sample inference through adaptive shrinkage of residual moments and cluster-specific covariance adjustment. The performance of FE-ARSC is evaluated using a Monte Carlo simulation study comprising 24 experimental scenarios that vary the cross-sectional dimension, time dimension, serial correlation, and heteroskedasticity. Each scenario is replicated 1,000 times, resulting in 24,000 simulated panel datasets. The proposed estimator is compared with conventional fixed-effects, cluster-robust, and Driscoll–Kraay covariance estimators using measures of bias, standard-error calibration, and confidence-interval coverage. The results indicate that FE-ARSC provides more accurate finite-sample inference across the simulated environments. The estimator achieves an average confidence-interval coverage probability of 94.9%, closely matching the nominal 95% level, and an estimated-to-empirical standard-error ratio of 1.0. The conventional fixed-effects, cluster-robust, and Driscoll–Kraay estimators achieve coverage probabilities of 91.5%, 93.2%, and 72.6%, respectively. Sensitivity analyses further confirm the robustness of the proposed methodology. These findings suggest that adaptive regularisation of residual moments can improve covariance estimation and statistical inference in short fixed-effects panel models. FE-ARSC offers a computationally straightforward and practical addition to existing covariance estimation methods.
Keywords
References
25 references- Andrews, D.W.K., 1991. Heteroskedasticity and autocorrelation consistent covariance matrix estimation. Econometrica, 59(3): 817–858.
- Arellano, M., 1987. Computing robust standard errors for within-groups estimators. Oxford Bulletin of Economics and Statistics, 49(4): 431–434.
- Bai, J., Choi, S.H., Liao, Y., 2015. Feasible generalized least squares for panel data with cross-sectional and serial correlation. Journal of Econometrics, 188(1): 54–75.
- Baltagi, B.H., 2021. Econometric Analysis of Panel Data. 6th ed., Springer, Cham, Switzerland, 424 p.
- Boot, T., Ligtenberg, J.W., 2025. Identification and many moment-robust inference via invariant moment conditions. Journal of Econometrics, 252: 106114.
- Cameron, A.C., Gelbach, J.B., Miller, D.L., 2011. Robust inference with multiway clustering. Journal of Business & Economic Statistics, 29(2): 238–249.
- Cameron, A.C., Miller, D.L., 2015. A practitioner's guide to cluster-robust inference. Journal of Human Resources, 50(2): 317–372.
- Carrasco, M., Nayihouba, A., 2024. Regularized estimation of dynamic panel models. Econometric Theory, 40(2): 360–418.
- Casini, A., Perron, P., 2023. Robust covariance matrix estimation in time series: a review. Econometrics and Statistics, 27: 36–61.
- De Nard, G., Zhao, Z., 2023. Using, taming or avoiding the factor zoo? A double-shrinkage estimator for covariance matrices. Journal of Empirical Finance, 72: 23–35.
- Driscoll, J.C., Kraay, A.C., 1998. Consistent covariance matrix estimation with spatially dependent panel data. Review of Economics and Statistics, 80(4): 549–560.
- Efron, B., Morris, C., 1977. Stein's paradox in statistics. Scientific American, 236(5): 119–127.
- Hansen, B.E., 2007. Asymptotic properties of a robust variance matrix estimator for panel data when T is large. Journal of Econometrics, 141(2): 597–620.
- Imbens, G.W., Kolesár, M., 2016. Robust standard errors in small samples: some practical advice. Review of Economics and Statistics, 98(4): 701–712.
- James, W., Stein, C., 1961. Estimation with quadratic loss. In: Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, Conference Proceedings Book, June 20–July 30, University of California Press, pp. 361–379.
- Juodis, A., Karabiyik, H., Westerlund, J., 2021. On the robustness of the pooled CCE estimator. Journal of Econometrics, 220(2): 325–348.
- Ledoit, O., Wolf, M., 2004. A well-conditioned estimator for large-dimensional covariance matrices. Journal of Multivariate Analysis, 88(2): 365–411.
- MacKinnon, J.G., 2002. Bootstrap inference in econometrics. Canadian Journal of Economics, 35(4): 615–645.
- MacKinnon, J.G., 2019. How cluster-robust inference is changing applied econometrics. Canadian Journal of Economics, 52(3): 851–881.
- MacKinnon, J.G., Nielsen, M.Ø., Webb, M.D., 2023a. Cluster-robust inference: a guide to empirical practice. Journal of Econometrics, 232(2): 272–299.
- MacKinnon, J.G., Nielsen, M.Ø., Webb, M.D., 2023b. Fast and reliable jackknife and bootstrap methods for cluster-robust inference. Journal of Applied Econometrics, 38(5): 671–694.
- MacKinnon, J.G., Nielsen, M.Ø., Webb, M.D., 2023c. Testing for the appropriate level of clustering in linear regression models. Journal of Econometrics, 235(2): 2027–2056.
- MacKinnon, J.G., White, H., 1985. Some heteroskedasticity-consistent covariance matrix estimators with improved finite sample properties. Journal of Econometrics, 29(3): 305–325.
- Romanov, E., Kur, G., Nadler, B., 2023. Tyler's and Maronna's M-estimators: non-asymptotic concentration results. Journal of Multivariate Analysis, 196: 105184.
- Wooldridge, J.M., 2010. Econometric Analysis of Cross Section and Panel Data. 2nd ed., MIT Press, Cambridge, Massachusetts, USA, 1096 p.
How to cite
APA
IEEE
MLA
Chicago
Harvard
Vancouver
BibTeX
RIS
Licence
May be shared and adapted with credit, for non-commercial purposes. Copyright © 2026 The copyright of the published article belongs to its author..