Empirical Bayes Inference for Generalized Exponential Distribution Based on Records
- 31 December 2004
- journal article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 33 (8) , 1851-1861
Abstract
Record values can be viewed as order statistics from a sample whose size is determined by the values and the order of occurrence of observations. Bayes and empirical Bayes estimators for the unknown parameter of the generalized exponential distribution are derived based on record statistics. These estimates are obtained based on squared error and LINEX loss functions. Prediction bounds for future lower record values are obtained by using Bayes and empirical Bayes techniques. Numerical example is given to illustrate the results.Keywords
This publication has 14 references indexed in Scilit:
- Inferences for generalized exponential distribution based on record statisticsJournal of Statistical Planning and Inference, 2002
- Bayesian Estimation, Prediction and Characterization for the Gumbel Model Based on RecordsStatistics, 2002
- Estimation of the location and scale parameters of generalized exponential distribution based on order statisticsJournal of Statistical Computation and Simulation, 2001
- Theory & Methods: Generalized exponential distributionsAustralian & New Zealand Journal of Statistics, 1999
- Risk behavior of variance estimators in multivariate normal distributionStatistics & Probability Letters, 1992
- Application of laplace approximation to record valuesCommunications in Statistics - Theory and Methods, 1990
- Record values and related statistics - a reviewCommunications in Statistics - Theory and Methods, 1988
- The future occurrence of recordsAnnals of the Institute of Statistical Mathematics, 1983
- Statistical Prediction Analysis1975
- Prior Distributions Fitted to Observed Reliability DataIEEE Transactions on Reliability, 1972