:: Volume 15, Issue 2 (3-2022) ::
JSS 2022, 15(2): 381-405 Back to browse issues page
Estimation and Prediction for the Poisson-Exponential Distribution Based on Records and Inter-Record Times: A Comparative Study
Firozeh Bastan, Seyed Mohamad Taghi Kamel MirMostafaee *
Abstract:   (2659 Views)

In this paper, estimation and prediction for the Poisson-exponential distribution are studied based on lower records and inter-record times. The estimation is performed with the help of maximum likelihood and Bayesian methods based on two symmetric and asymmetric loss functions. As it seems that the integrals of the Bayes estimates do not possess closed forms, the Metropolis-Hastings within Gibbs and importance sampling methods are applied to approximating these integrals. Moreover, the Bayesian prediction of future records is also investigated. A simulation study and an application example are presented to evaluate and show the applicability of the paper's results and also to compare the numerical results when the inference is based on records and inter-record times with those when the inference is based on records alone. 

Keywords: Metropolis-Hastings Within Gibbs Algorithm, Lower Record Statistics, Inter-Record Times, Monte Carlo Simulation, Importance Sampling.
Full-Text [PDF 290 kb]   (920 Downloads)    
Type of Study: Research | Subject: Statistical Inference
Received: 2020/03/27 | Accepted: 2022/03/1 | Published: 2021/10/4

XML   Persian Abstract   Print

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 15, Issue 2 (3-2022) Back to browse issues page