Bayesian estimation of heteroscedastic skew-normal error regression model

Document Type : Original Scientific Paper

Authors

Department of Statistics‎, ‎ University of Ilorin‎, ‎Nigeria

Abstract

In statistics‎, ‎errors are inherent in data and models‎, ‎particularly heteroscedasticity and skew-normal error structures‎. ‎These errors were simultaneously generated and infused into the data‎, ‎leading to uncertainty in parameter estimation‎. ‎The statistician uses statistical knowledge to elicit information and guide decision-making‎. ‎Both classical and Bayesian restricted Stein-rule least squares were compared when the data were contaminated with the aforementioned errors‎. ‎This study proposed an innovative Bayesian generalized restricted Stein-rule least squares method with heteroscedastic skew-normal errors‎, ‎which was ultimately found to be more efficient compared to non-Bayesian restricted Stein-rule least square estimators‎. ‎The study observed excellent performance of the Bayesian frameworks‎, ‎including the Bayes estimate and posterior mean‎, ‎in comparison to the classical restricted Stein-rule least squares estimators‎. ‎Therefore‎, ‎the study recommends Bayesian generalized restricted Stein-rule least squares to analysts and researchers who may encounter such errors in their data‎.

Keywords

Main Subjects

References


Alhamide, A.A., Kamarulzaman, I., Alodat, M.T. and Wan Z.W.Z. (2019). Bayesian inference for linear regression under alpha-skew-normal prior. Sains Malaysiana, 48(1):227–235.
Azzalini, A. (1985). A class of distributions which includes the normal ones. Scandinavian Journal of Statistics, 12(2):171–178.
Azzalini, A. (1986). Further results on a class of distributions which includes the normal ones. Statistica, 46(6):199–208.
Azzalini, A. (2005). The skew-normal distribution and related multivariate families. Scandinavian Journal of Statistics, 32(2):159–188.
Azzalini, A. and Dalla, V. (1996). The multivariate skew-normal distribution. Biometrika, 83(4):715–726.
Cepeda, E. and Germaman, D. (2000). Bayesian modelling of variance heterogeneity in normal regression models. Brazil Journal of Probability Statistics, 14(2):207–221.
Chaturvedi, A., Wan, A.T.K. and Singh, S.P. (2001). Stein-rule restricted regression estimator in a linear regression model with non-spherical disturbances. Communication in Statistical Theory Methods, 30(1):55–68.
Corrales, M.L. and Cepeda-Cuervo, E. (2022). Bayesian modelling of location, scale and shape parameters in skew-normal regression models. Statistical Analysis and Data Mining: The ASA Data Science Journal, 15(1):98–111.
Ferreira, J.T. and Steel, M.F. (2007). A new class of skewed multivariate distributions with applications to regression analysis. Statistica Sinica, 17(2):505–529.
Genton, M.G., He, L. and Liu, X. (2001). Moments of skew-normal random vectors and their quadratic forms. Statistics & Probability Letters, 51(4):319–325.
Harvey, A.C. (1976). Estimating regression models with multiplicative heteroscedasticity. Econometrica: Journal of the Econometric Society, 44(3):461–465.
Lachos, V.H., Bolfarine, H., Arellano-Valle, R.B. and Montenegro, L.C. (2007). Likelihood-based inference for multivariate skew-normal regression models. Communication Statistics Theory Methods, 36(9):1769–1786.
Indacochea, D. (2012). The Effects of skewness and kurtosis on heteroskedasticity-robust bootstrap methods in finite samples. Doctoral dissertation, Queen's University.
O'Hagan, A. and Leonard, T. (1976). Bayes estimation subject to uncertainty about parameter constraints. Biometrika, 63(1):201–203.
Oloyede, I. (2023). Bayesian linear restricted least squares estimators. Journal of the Indian Society for Probability and Statistics, 24(1):65–74.
Oloyede, I., Ipinyomi, R.A. and Iyaniwura, J.O. (2013). Bayesian generalized least squares with parametric heteroscedasticity linear model. Asian Journal of Mathematics and Statistics, 6:57–75.
R Core Team (2024). R: A Language and Environment for Statistical Computing. Version 4.22, R Foundation for Statistical Computing. https://www.R-project.org
Rubio, F.J. and Genton, M.G. (2016). Bayesian linear regression with skew-symmetric error distributions with applications to survival analysis. Statistics in Medicine, 35(14):2441–2454.
Journal of Statistical Modelling: Theory and Applications
Volume 5, Issue 2
July 2024
Pages 153-163

Files

History

  • Receive Date: 14 September 2024
  • Revise Date: 10 May 2025
  • Accept Date: 28 May 2025

Share

How to cite

Statistics