Two parameter Ridge estimator for the Bell regression model

Abstract

One solution to the multicollinearity problem in the Bell regression model, which is utilized for over-dispersion issues, is biased estimators. In recent years, some biased estimators have been proposed in the Bell regression model that can be used in modelling correlated count data. In this article, Bell two-parameter ridge estimator (BTPRE) is proposed. This two-parameter estimator has some advantages over the previously proposed estimators. More efficient results are obtained than the Maximum Likelihood estimator (MLE) and Bell Ridge estimator (BRE) in the case of multicollinearity by using BTPRE. Monte Carlo simulation study and real data results are obtained to show that the proposed estimator is better. Estimators have been compared according to the Mean Squared Error (MSE) criterion. BTPRE is superior to other estimators.

Keywords

• Regression
• count data
• overdispersion
• multicollinearity

References

1. Alheety, M. I., Qasim, M., M˚ansson, K., Kibria, B. M., Modified almost unbiased two parameter estimator for the Poisson regression model with an application to accident data, SORT, 45 (2021), 121-142. DOI: 10.2436/20.8080.02.112
2. Algamal, Y. A., Developing a ridge estimator for the gamma regression model, Journal of Chemometrics, (2018), 32. DOI: 10.1002/cem.3054
3. Algamal, Y. A., Performance of ridge estimato in inverse Gaussian regression model, Communications in Statistics-Theory and Methods, 48(15) (2019), 3836–3849. DOI: 10.1080/03610926.2018.1481977
4. Amin, M., Akram, M. N., Majid, A., On the estimation of Bell regression model using ridge estimator, Communications in Statistics-Simulation and Computation, (2021), https://doi.org/10.1080/03610918.2020.1870694
5. Asar, Y., Genç, A., Two-parameter Ridge estimator in the binary logistic regression, Comm. Statist. Simulation Comput., 46(9) (2017), 7088–7099. DOI: 10.1080/03610918.2016.1224348
6. Bell, E. T., Exponential numbers, The American Mathematical Monthly, 41(7) (1934), 411–419.
7. Bulut, Y. M., Işılar, M., Two parameter Ridge estimator in the inverse Gaussian regression model, Hacettepe Journal of Mathematics and Statistics, 50(3) (2021), 895–910. DOI: 10.15672/hujms.813540
8. Castellares, F., Ferrari, S. L. P., Lemonte, A. J., On the Bell distribution and its associated regression model for count data, Applied Mathematical Modelling, 56 (2018), 172–185. DOI: 10.1016/j.apm.2017.12.014

9. Hoerl, A. E., Kennard, R. W., Ridge regression: Biased estimation for nonorthogonal problems, Technometrics, 42(1) (1970), 80–86, http://www.jstor.org/stable/1271436
10. Lipovetsky, S., Two parameter Ridge regression and its convergence o the eventual pairwise model, Math Comput Model, 44 (2006), 304–318. DOI: 10.1016/j.mcm.2006.01.017
11. Lipovetsky, S., Conklin, W. M., Ridge regression in two-parameter solution, Appl. Stoch. Models Bus. Ind., 21(6) (2005), 525–540. DOI: 10.1002/asmb.603
12. Mansson, K., On ridge estimators for the negative binomial regression model, Economic Modelling, 29 (2012), 178–184. DOI: 10.1016/j.econmod.2011.09.009
13. Mansson, K., Shukur, G., A Poisson ridge regression estimator, Econ. Model., 28 (2011), 1475–1481. DOI: 10.1016/j.econmod.2011.02.030
14. McDonald, G. C., Galarneau, D. I., A monte carlo evaluation of some ridge-type estimators, Journal of the American Statistical Association, 70(350) (1975), 407–416.
15. Myers, R., Montgomery, D., Vining, G., Robinson, T., Generalized Linear Models with Applications in Engineering and the Sciences, Second Edition, Wiley, A John Wiley Sons, Inc., Publication, 2012.
16. Newhouse, J. P., Oman, S. D., An evaluation of ridge estimators, Rand Corporation (p-716-PR), Santa Monica, (1971), 1–16, https://doi.org/10.1080/00949655.2018.1498502
17. Qasim, M., Kibria, B. M. G., M˚ansson, K., Sjolander, P., A new Poisson Liu regression estimator: method and application, Journal of Applied Statistics, 47(12) (2020), 2258–2271. DOI: 10.1080/02664763.2019.1707485
18. Qasim, M., Bulut, Y. M., Mansson, K., The Wald-type confidence interval on the mean response function of the Poisson inverse Gaussian Ridge regression, Accepted: October 2023. REVSTAT-Statistical Journal.
19. R Core Team, R: A Language and Environment for Statistical Computing, Vienna, Austria: R Foundation for Statistical Computing, 2014, http://www.R-project.org/
20. Scahaefer, R. L., Roi, L. D., Wolfe, R. A., A ridge logistic estimator, Communications in Statistics-Theory and Methods, 13 (1984), 99–113.
21. Toker, S., Ka¸cıranlar, S., On the performance of two parameter ridge estimator under the mean square error criterion, Appl. Math. Comput., 219 (2013), 4718–4728. DOI: 10.1016/j.amc.2012.10.088