New families of discrete distributions are obtained by inverting non-negative integer-valued discrete distributions. Two methods, namely P-inverting and Q-inverting are proposed. The “P-inverse” is generated from a non-increasing probability mass function (PMF), while “Q-inverse” results in a non-increasing PMF. Some relations between the original and the generated distributions are established. Models are shown to give good fits for some well-known datasets.
KatzL. Characteristics of Frequency Functions Defined by First Order Difference Equations, Ph.D. Thesis. Ann Arbor, MI: University of Michigan.1945.
2.
KempAW. AWide Class of Discrete Distributions and their Associated Differential Equations. Sankhya Series A. 1968; 30(4): 401–410.
3.
JohnsonNLKempAWKotzS. Univariate Discrete Distributions. New York: John Wiley and Sons.2005.
4.
AljarrahMALeeCFamoyeF. On Generating T-X Family of Distributions Using Quantile Functions. J Stat Dist App. 2014; 1(1): 1–17.
5.
AlzaatrehALeeCFamoyeF. On the Discrete Analogues of Continuous Distributions. Stat Meth. 2012; 9(6):589–603.
6.
ChakrabortyS. Generating Discrete Analogues of Continuous Probability Distributions---A Survey of Methods and Constructions. J Stat Dist App. 2015; 2(1): 6.
7.
SankaranM. The Discrete Poisson-Lindley Distribution. Bio. 1970; 26(1): 145–149.
8.
YuleGU. A Mathematical Theory of Evolution, Based on the Conclusions of Dr. J.C. Willis, F.R.S. Phil Tran Roy Soc London. Series B. 1925; 213: 21–87.
9.
RoyD. The Discrete Normal Distribution. Commun Stat---Theory Methods. 2003; 32(10): 1871–1883.
10.
GómezED. A New Discrete Distribution: Properties and Applications in Medical Care. J App Stat. 2013; 40(12): 2760–2770.
11.
KendallMG. Natural Law in the Social Sciences. J Roy Stat Soc. A (General). 1961; 124: 1–19.
