The Cos-Poisson model with a novel count regression analysis

Abstract

In this paper, we propose a new generalization of the Poisson distribution by using the concept of the weighted distribution; a trigonometric weight with the cosine function is used. We derive some distributional properties of the new distribution, such as the cumulative distribution function, moment generating function, factorial moments, and index of dispersion. Then, the related model is considered for modeling purposes, with estimation of the model parameters performed via several methods. Zero-inflated count regression analysis is introduced by using the new distribution. Finally, we provide two applications of the obtained results on practical data sets.

Keywords

• confidence interval
• count data
• count regression
• index of dispersion
• zero-inflated data

References

1. [1] Y. Akdoğan, C. Kuş, A. Asgharzadeh, İ. Kınacı and F. Sharafi, Uniform-geometric distribution, J. Stat. Comput. Simul. 86 (9), 1754-1774, 2016.
2. [2] A. Atkinson, Two graphical displays for outlying and influential observations in regression, Biometrika 68 (1), 13-20, 1981.
3. [3] H.S. Bakouch, A weighted negative binomial Lindley distribution with applications to dispersed data, An. Acad. Brasil. Ciênc. 90 (3), 2617-2642, 2018.
4. [4] D. Bhati and S. Joshi, Weighted geometric distribution with a new characterization of geometric distribution, Comm. Statist. Theory Methods 47 (6), 1510-1527, 2018.
5. [5] A.C. Cameron, P.K. Trivedi, F. Milne and J. Piggott, A microeconomic model of the demand for health care and health insurance in Australia, Rev. Econ. Stud. 55 (1), 85-106, 1988.
6. [6] J.D. Castillo and M.P. Casany, Weighted Poisson Distributions and under dispersion Situations, Ann. Inst. Statist. Math. 5, 567-585, 1998.
7. [7] C. Chesneau, H.S. Bakouch, T. Hussain and B.A. Para, The cosine geometric distribution with count data modeling, J. Appl. Stat. 48 (1), 124-137, 2021.
8. [8] D.A.S. Fraser, Probability and Statistics: Theory and Applications, North Scituate MA, Duxbury Press, 1976.

9. [9] M.G. Kendall, Natural law in social sciences, J. Roy. Statist. Soc. Ser. A 124, 1-19, 1961.
10. [10] M.S.A. Khan, A. Khalique and A.M. Abouammoh, On estimating parameters in a discrete, Weibull distribution, IEEE Trans. Reliab. 38 (3), 348-350, 1989.
11. [11] C. Kuş, Y. Akdoğan, A. Asgharzadeh, İ. Kınacı and K. Karakaya, Binomial-discrete Lindley distribution, Commun. Fac. Sci. Univ. Ank. Ser. A1. Math. Stat. 68 (1), 401-411, 2018.
12. [12] A.J. Lemonte, G. Moreno-Arenas and F. Castellares, Zero inflated Bell regression models for count data, J. Appl. Stat. 47 (2), 265-286, 2020.
13. [13] G.P. Patil and C.R. Rao, The weighted distributions: A survey and their applications, in: Krishnaiah, P.R. (ed.) Applications of statistics, North-Holland Publ. Co., Amsterdam, 1977.
14. [14] G.P. Patil and C.R. Rao, Weighted distributions and size biased sampling with applications to wild-life populations and human families, Biometrica 34, 179-189, 1978.
15. [15] C.R. Rao, On discrete distributions arising out of methods of ascertainment, Sankhya A, 311-324, 1965.