Back to Search
Start Over
A new one-parameter lifetime distribution and its regression model with applications
- Source :
- PLoS ONE, PLOS ONE, PLoS ONE, Vol 16, Iss 2, p e0246969 (2021)
- Publication Year :
- 2021
- Publisher :
- Public Library of Science, 2021.
-
Abstract
- Lifetime distributions are an important statistical tools to model the different characteristics of lifetime data sets. The statistical literature contains very sophisticated distributions to analyze these kind of data sets. However, these distributions have many parameters which cause a problem in estimation step. To open a new opportunity in modeling these kind of data sets, we propose a new extension of half-logistic distribution by using the odd Lindley-G family of distributions. The proposed distribution has only one parameter and simple mathematical forms. The statistical properties of the proposed distributions, including complete and incomplete moments, quantile function and Rényi entropy, are studied in detail. The unknown model parameter is estimated by using the different estimation methods, namely, maximum likelihood, least square, weighted least square and Cramer-von Mises. The extensive simulation study is given to compare the finite sample performance of parameter estimation methods based on the complete and progressive Type-II censored samples. Additionally, a new log-location-scale regression model is introduced based on a new distribution. The residual analysis of a new regression model is given comprehensively. To convince the readers in favour of the proposed distribution, three real data sets are analyzed and compared with competitive models. Empirical findings show that the proposed one-parameter lifetime distribution produces better results than the other extensions of half-logistic distribution.
- Subjects :
- Science
Materials Science
Research and Analysis Methods
01 natural sciences
010104 statistics & probability
Probability theory
Carbon Fiber
0502 economics and business
Applied mathematics
0101 mathematics
Materials
Statistical hypothesis testing
Mathematics
Statistical Data
050210 logistics & transportation
Likelihood Functions
Multidisciplinary
Models, Statistical
Estimation theory
Statistical Models
Simulation and Modeling
05 social sciences
Statistics
Regression analysis
Random Variables
Quantile function
Probability Theory
Probability Distribution
Fibers
Skewness
Physical Sciences
Probability distribution
Medicine
Regression Analysis
Random variable
Research Article
Statistical Distributions
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 16
- Issue :
- 2
- Database :
- OpenAIRE
- Journal :
- PLoS ONE
- Accession number :
- edsair.doi.dedup.....45a05a880ac4064234721f6f04f08ecd