International Journal of Transformations in Business Management

International Peer Reviewed (Refereed), Open Access Research Journal

E-ISSN : 2231-6868 | P-ISSN : 2454-468X

IMPACT FACTOR : 5.987 | SJIF 2020: 6.336 | ICV 2020=66.47

+91 9555269393 | +91 9311631393   info@ijtbm.com


Abstract

Robust Multicollinearity Diagnostic and Remedy in High-Dimensional Fixed Effect Panel Data Using Support Vector Regression

Abdullah Mohammed Rashid

Department of Accounting and Financial Control, College of Business Economics, Al-Nahrain University, Iraq.

31-44 Vol: 16, Issue: 4, 2026
Receiving Date: 2026-09-11
Acceptance Date: 2026-10-05
Publication Date: 2026-10-31
Download PDF

http://doi.org/10.37648/ijtbm.v16i04.004

Abstract

Multicollinearity in fixed effect panel data models inflates the variances of the within-group estimator and undermines statistical inference. High leverage collinearity-enhancing observations (HLCEOs), a class of outliers in the predictor space, can create spurious collinearity that the classical variance inflation factor (CVIF) cannot distinguish from genuine dependence among the regressors. Existing robust VIF diagnostics for panel data rely on Mahalanobis-type leverage detection, which deteriorates as the number of predictors p grows relative to the number of observations. This paper makes two contributions. First, we propose the support vector regression variance inflation factor (SVRVIF), a robust diagnostic that replaces the ordinary least squares auxiliary regressions of the classical VIF with ε-insensitive support vector regressions (SVR) fitted to robustly within-transformed data. Second, we propose the within-group SVR (WGSVR) estimator as a remedy when genuine multicollinearity and HLCEO contamination occur together. Monte Carlo experiments with n ∈ {10, 50, 100} individuals, T ∈ {10, 20} periods, p ∈ {20, 50, 100} predictors and contamination levels of 5% and 10% show that HLCEOs inflate the CVIF to values above 50, whereas the SVRVIF stays close to 1 in every configuration examined. Under genuine multicollinearity with 10% contamination, the WGSVR estimator attains the smallest mean squared error among the within-group OLS, WGM-FIMGT and WGSVR estimators, and its advantage grows with p. Two empirical applications, to the Greene airline panel and to a 40-predictor macroeconomic growth panel, support the simulation findings.

Keywords: Fixed effect panel data; high-dimensional regression; high leverage points; multicollinearity; robust diagnostics; support vector regression; variance inflation factor; within-group estimator

References

  1. Bagheri, A., & Midi, H. (2011). On the performance of robust variance inflation factors. International Journal of Agricultural and Statistical Sciences, 7(1), 31–45.
  2. Bagheri, A., Midi, H., & Imon, A. H. M. R. (2012). A novel collinearity-influential observation diagnostic measure based on a group deletion approach. Communications in Statistics – Simulation and Computation, 41(8), 1379– 1396. https://doi.org/10.1080/03610918.2012.625332
  3. Baltagi, B. H. (2008). Econometric analysis of panel data (4th ed.). John Wiley & Sons.
  4. Bramati, M. C., & Croux, C. (2007). Robust estimators for the fixed effects panel data model. The Econometrics Journal, 10(3), 521–540. https://doi.org/10.1111/j.1368-423X.2007.00220.x
  5. Chang, C.-C., & Lin, C.-J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3), Article 27. https://doi.org/10.1145/1961189.1961199
  6. Croissant, Y., & Millo, G. (2008). Panel data econometrics in R: The plm package. Journal of Statistical Software, 27(2), 1–43. https://doi.org/10.18637/jss.v027.i02
  7. Greene, W. H. (2007). Econometric analysis (6th ed.). Prentice Hall
  8. Habshah, M., Norazan, M. R., & Imon, A. H. M. R. (2009). The performance of diagnostic-robust generalized potentials for the identification of multiple high leverage points in linear regression. Journal of Applied Statistics, 36(5), 507–520. https://doi.org/10.1080/02664760802553463
  9. Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multivariate data analysis (8th ed.). Cengage.
  10. Hall, P., Marron, J. S., & Neeman, A. (2005). Geometric representation of high dimension, low sample size data. Journal of the Royal Statistical Society: Series B, 67(3), 427–444. https://doi.org/10.1111/j.1467- 9868.2005.00510.x
  11. Ismaeel, S. S., & Midi, H. (2018). Robust within group estimator for fixed effect panel data. Pakistan Journal of Statistics, 34(4), 297–310.
  12. Ismaeel, S. S., Midi, H., & Sani, M. (2021). Robust multicollinearity diagnostic measure for fixed effect panel data model. Malaysian Journal of Fundamental and Applied Sciences, 17, 636–646. https://doi.org/10.11113/mjfas.v17n5.2407
  13. Kamruzzaman, M., & Imon, A. H. M. R. (2002). High leverage point: Another source of multicollinearity. Pakistan Journal of Statistics, 18(3), 435–448.
  14. Lim, H. A., & Midi, H. (2016). Diagnostic robust generalized potential based on index set equality (DRGP(ISE)) for the identification of high leverage points in linear model. Computational Statistics, 31(3), 859–877. https://doi.org/10.1007/s00180-016-0638-y
  15. Maronna, R. A., Martin, R. D., & Yohai, V. J. (2006). Robust statistics: Theory and methods. John Wiley & Sons. https://doi.org/10.1002/0470010940
  16. Midi, H., Sani, M., Ismaeel, S. S., & Arasan, J. (2021). Fast improvised influential distance for the identification of influential observations in multiple linear regression. Sains Malaysiana, 50(7), 2085–2094. https://doi.org/10.17576/jsm-2021-5007-24
  17. Montgomery, D. C., Peck, E. A., & Vining, G. G. (2012). Introduction to linear regression analysis (5th ed.). John Wiley & Sons.
  18. O’Brien, R. M. (2007). A caution regarding rules of thumb for variance inflation factors. Quality & Quantity, 41(5), 673–690. https://doi.org/10.1007/s11135-006-9018-6
  19. Rousseeuw, P. J., & Leroy, A. M. (1987). Robust regression and outlier detection. John Wiley & Sons. https://doi.org/10.1002/0471725382
  20. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199– 222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
  21. Steinwart, I., & Christmann, A. (2008). Support vector machines. Springer. https://doi.org/10.1007/978-0-387-77242- 4
  22. Vapnik, V. N. (1995). The nature of statistical learning theory. Springer. https://doi.org/10.1007/978-1-4757-3264-1
  23. World Bank. (2023). World development indicators [Data set]. https://data.worldbank.org
Back

```