The log-weighted exponential regression model: alternative to the beta regression model. Issue 10 (19th May 2021)

• Record Type: Journal Article
• Authors: Altun, Emrah
• Is Part Of: Communications in statistics. Volume 50:Issue 10(2021)
• Page Start: 2306
• Page End: 2321
• Publication Date: 2021-05-19
• Subjects: Weighted-exponential -- method of moments -- residual analysis -- beta regression; 62E15; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2019.1664586
• Languages: English
• ISSNs: 0361-0926

Abstract

Abstract: In this paper, we introduce a new two-parameter distribution, called log-weighted exponential (log-WE) distribution, defined on the unit interval. Some of the statistical properties of the proposed distribution including moments, incomplete moments and mean residual life function are obtained. The maximum likelihood, method of moments, least squares and weighted least squares estimation methods are used to estimate unknown parameters of the proposed model and finite sample performance of estimation methods are evaluated through Monte-Carlo simulation study. Moreover, a new regression model as an alternative to the beta regression model is introduced.