Classical and Bayesian Estimation of Entropy for Pareto Distribution in Presence of Outliers with Application

Amal S. Hassan (), E. A. Elsherpieny () and Rokaya E. Mohamed ()
Additional contact information
Amal S. Hassan: Faculty of Graduate Studies for Statistical Research
E. A. Elsherpieny: Faculty of Graduate Studies for Statistical Research
Rokaya E. Mohamed: Faculty of Graduate Studies for Statistical Research

Sankhya A: The Indian Journal of Statistics, 2023, vol. 85, issue 1, No 29, 707-740

Abstract: Abstract The measure of entropy has a pivotal role in the information theory area. In this paper, estimation of differential entropy for Pareto distribution in presence of r outliers is considered. In this regard, the classical and Bayesian estimation techniques of differential entropy are employed. In classical setup, we obtain the maximum likelihood estimators of the differential entropy as well as assessing their performance via a simulation study. The entropy Bayesian estimator is derived using squared error, linear exponential, weighted squared error and K loss functions. The Metropolis-Hastings algorithm is used to generate posterior random variables. Monte Carlo simulations are designed to implement the precision of estimates for different sample sizes and number of outliers. Furthermore, performance of estimates is planned by experiments with real data. Generally, we conclude that the entropy Bayesian estimates of simulated data tend to the true value as the number of outliers increases. Further, the entropy Bayesian estimate under weighted squared error loss function is preferable to the other estimates in majority of situations.

Keywords: Pareto distribution; Outliers; Differential entropy; Metropolis- Hastings algorithm; Primary: 65C05; Secondary: 62F15, 62G05 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s13171-021-00274-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sankha:v:85:y:2023:i:1:d:10.1007_s13171-021-00274-z

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/13171

DOI: 10.1007/s13171-021-00274-z

Access Statistics for this article

Sankhya A: The Indian Journal of Statistics is currently edited by Dipak Dey

More articles in Sankhya A: The Indian Journal of Statistics from Springer, Indian Statistical Institute
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().