Post Improved Estimation and Prediction in the Gamma Regression Model

Authors

  • Pannipa Rintara Department of Mathematics and Statistics, Faculty of Science and Technology, Thammasat University, Pathum Thani, Thailand
  • Syed Ejaz Ahmed Department of Mathematics and Statistics, Brock University, St. Catharines, Ontario, Canada
  • Supranee Lisawadi Department of Mathematics and Statistics, Faculty of Science and Technology, Thammasat University, Pathum Thani, Thailand

Keywords:

Ridge, linear shrinkage, shrinkage pretest, LASSO, elastic net

Abstract

In this paper, we consider the estimation of regression coeffcients for a gamma regression model when multicollinearity is present. We suggest pretest and shrinkage estimation strategies based on ridge estimation and compare their performance with some penalty estimators. We investigate the asymptotic properties of the suggested estimators. A Monte Carlo simulation run to evaluate their performance confirmed that the suggested estimators outperformed the unrestricted ridge regression estimator. Finally, a real dataset was analyzed to demonstrate the practicality of the suggested ridge- type and penalty estimators.

References

Ahmed SE. Shrinkage preliminary test estimation in multivariate normal distributions. J Stat Comput Simul. 1992; 43(3-4): 177-195.

Ahmed SE. Penalty, shrinkage and pretest strategies: variable selection and estimation. New York: Springer; 2014.

Ahmed SE, Yüzbaşı B. Big data analytics: integrating penalty strategies. Int J Manag Sci Eng Manag. 2016; 11(2): 105-115.

Algamal ZY, Asar Y. Liu-type estimator for the gamma regression model. Commun Stat Simul Comput. 2020; 49(8): 2035-2048.

Amin M, Qasim M, Amanullah M, Afzal S. Performance of some ridge estimators for the gamma regression model. Stat Pap. 2020; 61(3): 997-1026.

Amin M, Qasim M, Yasin A, Amanullah M. Almost unbiased ridge estimator in the gamma regression model. Commun Stat Simul Comput. 2022; 51(7): 3830-3850.

Bancroft TA. On biases in estimation due to the use of preliminary tests of significance. Ann Math Stat. 1944; 15(2): 190-204.

Cepeda-Cuervo E, Corrales M, Cifuentes-Amada MV, Zarate H. On Gamma Regression Residuals. J Iran stat soc. 2016; 15(1): 29-44.

Hoerl AE. Application of ridge analysis to regression problems. Chem Eng Progr. 1962; 58(3): 54-59.

Johnson RA, Wichern DW. Applied multivariate statistical analysis. New Jersey: Pearson Education, Inc; 2002.

Judge GG, Bock ME. The statistical implications of pre-test and Stein-rule estimators in econometrics. New York: North-Holland Pub. Co; 1978.

Knight K, Fu W. Asymptotics for lasso-type estimators. Ann Stat. 2000; 28(5): 1356-1378.

Mahmoudi A, Arabi Belaghi R, Mandal S. A comparison of preliminary test, Stein-type and penalty estimators in gamma regression model. J Stat Comput Simul. 2020; 90(17): 3051-3079.

Reangsephet O, Lisawadi S, Ahmed SE. Adaptive Estimation Strategies in Gamma Regression Model. J Stat Theory Pract. 2020a; 14: 8.

Reangsephet O, Lisawadi S, Ahmed SE. Post Selection Estimation and Prediction in Poisson Regression Model. Thail Stat. 2020b; 18(2): 176-195.

Weissfeld LA, Sereika SM. A multicollinearity diagnostic for generalized linear models. Commun Stat Theory Methods. 1991; 20(4): 1183-1198.

Yüzbaşı B, Ahmed SE, Aydn D. Ridge-type pretest and shrinkage estimations in partially linear models. Stat Pap. 2020; 61(2): 869-898.

Downloads

Published

2023-06-28

How to Cite

Rintara, P. ., Ejaz Ahmed, S. ., & Lisawadi, S. . (2023). Post Improved Estimation and Prediction in the Gamma Regression Model. Thailand Statistician, 21(3), 580–606. Retrieved from https://ph02.tci-thaijo.org/index.php/thaistat/article/view/250068

Issue

Vol. 21 No. 3 (2023): July

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.