In regression analysis involving response variable on the bounded unit interval [0, 1], the beta regression model often suffice as a common choice, however, there are many alternatives to the beta regression model. In this article, we add yet another new alternative to the literature called the unit upper truncated Weibull (unit UTW) regression model. We introduce a novel unit UTW distribution as an alternative to the beta distribution and we present some of its mathematical properties. The unit UTW distribution is then extended to build the unit UTW regression model. Through an extensive Monte-Carlo simulation experiments, we show that the method of maximum likelihood can provide good estimate for each parameter in the new models. We give two practical examples were the proposed models performed better than the beta distribution and the beta regression model.
|Journal||Annals of Data Science|
|State||Accepted/In press - 2022|
Bibliographical notePublisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
- Beta distribution
- Bounded data
- Regression analysis
- Upper truncated Weibull
ASJC Scopus subject areas
- Business, Management and Accounting (miscellaneous)
- Computer Science Applications
- Statistics, Probability and Uncertainty
- Artificial Intelligence