A New Odd Exponential-Weibull Distribution with Applications to Survival Dataset

Musa Ndamadu Farouq¹, Nweze, N. O.², Adenomon, M. O. ², Adehi, M. U. ²

Abstract

Survival data are very common in clinical, chemical, and agronomic assays, among others. However, in practice, experiments are conducted so that all sample units are evaluated at the same time. These data are referred to as grouped survival data, which are a particular case of interval censoring and are characterized by an excessive number of ties. The study examines some of the existing parametric distributional models in accommodating various datasets and develops an extension termed the new odd exponential-Weibull distribution with applications to survival datasets. The research methodology used PDF and CDF plots of the Odd Exponential-Weibull Distribution keeping one parameter constant and varying others. The results presented in Table 1 reflect the comparative analysis of some statistical models fitted to the AAML dataset, with an emphasis on their goodness-of-fit measures. The table provides parameters and their estimates for each model, along with standard errors and various goodness-of-fit criteria such as Log-Likelihood (LL), Akaike Information Criterion (AIC), Consistent Akaike Information Criterion (CAIC), Bayesian Information Criterion (BIC), and Hannan-Quinn Information Criterion (HQIC). The log-likelihood (LL) values indicate the likelihood of the data given the model parameters. Among the models, the OEW model has the highest LL (-391.3732), suggesting it provides the best fit to the data by maximizing the likelihood. The AIC values assess the trade-off between the goodness of fit and the complexity of the model, where lower values indicate a better model. The research concluded by building upon privious work, this new distribution enhanced flexibility across several datasets. Thus, the study introduced the new distribution and evaluated its performance using lifetime and survival datasets. In addition, the research established the potential of the developed new distribution and its variants as promising alternatives in modelling positive data.

Keywords

survival; applications; new; odd; exponential;  Weibull; distribution

Cite This Article

Farouq, M. N., Nweze, N. O., Adenomon, M. O., Adehi, M. U. (2024). A New Odd Exponential-Weibull Distribution with Applications to Survival Dataset. International Journal of Scientific Advances (IJSCIA), Volume 5| Issue 5: Sep-Oct 2024, Pages 874-883, URL: https://www.ijscia.com/wp-content/uploads/2024/09/Volume5-Issue5-Sep-Oct-No.660-874-883.pdf

Volume 5 | Issue 5: Sep-Oct 2024