Open AccessBivariate discrete Nadarajah and Haghighi distribution: Properties and different methods of estimation
Author(s) -
Sajid Ali,
Muhammad Shafqat,
Ismail Shah,
Sanku Dey
Publication year - 2019
Publication title -
filomat
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.449
H-Index - 34
eISSN - 2406-0933
pISSN - 0354-5180
DOI - 10.2298/fil1917589a
Subject(s) - bivariate analysis , mathematics , bivariate data , extension (predicate logic) , statistics , exponential function , exponential family , distribution (mathematics) , exponential distribution , discrete modelling , econometrics , algorithm , computer science , discrete system , mathematical analysis , programming language
The exponential distribution is commonly used to model different phenomena in statistics and reliability engineering. A new extension of exponential distribution known as the Nadarajah and Haghighi [An extension of the exponential distribution, Statistics: A Journal of Theoretical and Applied Statistics 45 (2011) 543-558.] distribution was introduced in the literature to accommodate the inflation of zero in the data. In practice, however, discrete data are easy to collect as compared to continuous data. Discrete bivariate distributions play important roles in modeling bivariate lifetime count data. Thus focusing on the utility of discrete data, this study presents a new bivariate discrete Nadarajah and Haghighi distribution. We discuss some basic properties of the proposed distribution and study seven different methods of estimation for the unknown parameters to assess the performance of the proposed bivariate discrete model. Two data sets are also analyzed to demonstrate how the proposed model may work in practice. Results show that the proposed model is very flexible and performs better than some of the existing models.