On dynamic cumulative past inaccuracy measure based on extropy
Majid Hashempour, Morteza Mohammadi
Abstract
An alternate measure of extropy based on the cumulative distribution function rather than the probability density function of a random variable is called the cumulative past extropy (CPE). In this communication, the concept of CPE has been extended to cumulative past extropy inaccuracy (CPEI) and then to a dynamic version of it. A characterization problem for the proposed dynamic extropy inaccuracy measure has been studied under the proportional reversed hazard rate model. We also discuss the stochastic ordering of dynamic cumulative past extropy and certain results based on it. Some well-known lifetime distributions have been characterized using the proposed dynamic cumulative past extropy inaccuracy (DCPEI) measure. Three methods for nonparametric estimation of the DCPEI measure based on kernel and empirical estimators are proposed. Simulation results show that the kernel-based estimators of the DCPEI measure perform better than the empirical-based estimator under different sample sizes and times. A real data set is considered to show the behavior of the estimators in real cases.