Affiliation:
1. Departamento de Matemáticas y Estadística, Universidad del Norte, Barranquilla 080001, Colombia
Abstract
We propose the “Marshall–Olkin Bivariate Weibull Model with Modified Singularity MOBW-μ”, which focuses on bivariate distributions essential for reliability and survival analyses. Distributions such as the Marshall–Olkin bivariate exponential (MOBE) and the Marshall–Olkin bivariate Weibull (MOBW) are discussed. The MOBW-μ model is introduced, which incorporates a lag parameter μ in the singular part, and probabilistic properties such as the joint survival function, marginal density functions, and the bivariate hazard rate function are explored. In addition, aspects such as the correlation structure and survival copulation are addressed and we show that the correlation of the MOBW-μ is always lower than that of its copula, regardless of the parameters. The latter result implies that the MOBW-μ does not have the Lancaster’s phenomenon that explains that any nonlinear transformation of variables decreases the correlation in absolute value. The article concludes by presenting a robust theoretical framework applicable to various disciplines.
Reference36 articles.
1. Lancaster bivariate probability distributions with Poisson, negative binomial and gamma margins;Koudou;Test,1998
2. Sarabia, J.M., Prieto, F., and Jordá, V. (2014). Bivariate beta-generated distributions with applications to well-being data. J. Stat. Distrib. App., 1.
3. Bivariate joint models for survival and change of cognitive function;Pan;Stat. Methods Med. Res.,2023
4. A Multivariate Exponential Distribution;Marshall;J. Am. Stat. Assoc.,1967
5. Barlow, R., and Proschan, F. (1982). Statistical Theory of Reliability and Life Testing: Probability Models, To Begin With. [1st ed.].