Stein's Method for Poisson-Exponential Distributions
From MaRDI portal
Abstract: The distribution of the maximum of a zero truncated Poisson number of i.i.d. exponentially distributed random variables is known as a Poisson-Exponential distribution. This distribution arises for example as a model for monotone hazard rates and has its application in reliability studies. In this paper we first develop Stein's method for Poisson-Exponential distributions. We then provide upper bounds on the approximation errors in total variation distance when approximating Poisson-Exponential distributions and a Generalized Poisson-Exponential distribution by different Poisson-Exponential distributions. Moreover, employing standardized Stein equations we obtain upper bounds on the bounded Wasserstein distance when using a Poisson-Exponential distribution to approximate the distribution of maxima of a zero truncated Poisson number of i.i.d. geometric random variables. The results are applied to assess the bounded Wasserstein distance between a distribution of the maximum waiting time of the occurrence of Bernoulli sequence patterns and a Poisson-Exponential distribution. We illustrate the results numerically by approximating a Generalized Poisson-Exponential distribution with Poisson-Exponential distributions on two real data sets.
This page was built for publication: Stein's Method for Poisson-Exponential Distributions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6420991)
