https://cris.library.msu.ac.zw//handle/11408/322 2026-06-29T05:22:39Z 2026-06-29T05:22:39Z Nkomo, Wilbert Broderick Oluyede Thayaone Moakofi Chipepa, Fastel Charumbira, Welington Fredrick https://cris.library.msu.ac.zw//handle/11408/7125 2026-06-18T07:59:46Z 2026-01-01T00:00:00Z

Title: The new heavy-tailed Weibull exponentiated half logistic-G family of distributions: Properties, actuarial measures and inference Authors: Nkomo, Wilbert; Broderick Oluyede; Thayaone Moakofi; Chipepa, Fastel; Charumbira, Welington Fredrick Abstract: Accurate statistical modeling of complex real-world data, characterized by heavy tails, skewness, and non-monotonic hazard rates, presents a significant challenge that often exceeds the capabilities of traditional distributions. To address this, we introduce the Heavy-Tailed Weibull Exponentiated Half Logistic-G (HT-W-EHL-G) family of distributions, a novel flexible framework that synthesizes extreme-value robustness with versatile hazard rate shapes. This paper derives the fundamental statistical properties of the proposed family and establishes six estimation methods, whose efficiency is verified via Monte Carlo simulation. The model's practical utility is demonstrated by its robustness to censored data, a critical requirement in survival and reliability analysis, and its direct applicability for computing key actuarial risk measures, including Value at Risk (VaR) and Tail Value at Risk (TVaR). Extensive empirical analyses across diverse domains confirm the model's efficacy and statistically significant superiority in goodness-of-fit over established benchmarks.

2026-01-01T00:00:00Z Nkomo, Wilbert Broderick Oluyede Thayaone Moakofi Chipepa, Fastel Charumbira, Welington Fredrick Charumbira, Wellington Broderick Oluyede Fastel Chipepa https://cris.library.msu.ac.zw//handle/11408/6877 2025-10-28T09:24:52Z 2025-01-01T00:00:00Z

Title: The New Topp-Leone Exponentiated Half Logistic-Gompertz-G Family of Distributions with Applications Authors: Charumbira, Wellington; Broderick Oluyede; Fastel Chipepa Abstract: This research introduces a new family of distributions (FoD) titled the Topp-Leone Exponentiated-Half-Logistic-Gompertz-G (TL-EHL-Gom-G) distribution. The study explores a variety of statistical properties of the developed family, such as the quantile function, series expansion, order statistics, entropy, stochastic orders and moments. Through Monte Carlo simulations, various estimation techniques were compared, including the least squares (LS), Anderson Darling (AD), maximum likelihood (ML) and Cram\'er-von-Mises (CVM) methods via root mean square error (RMSE) and average bias (Abias). The results indicated that the ML estimation method performed better than other methods, hence, the selection for estimating the model parameters. To showcase the usefulness, robustness and applicability of the model, we applied it to three real-life data, including dataset with censored observations. The TL-EHL-Gom-W distribution, a special case of the TL-EHL-Gom-G FoD showed superiority over nested and non-nested models.

2025-01-01T00:00:00Z Charumbira, Wellington Broderick Oluyede Fastel Chipepa Chipepa, Fastel Mahmoud M. Abdelwahab Charumbira, Wellington Fredrick Mustafa M. Hasaballah https://cris.library.msu.ac.zw//handle/11408/6873 2025-10-28T07:40:23Z 2025-01-01T00:00:00Z

Title: A New Topp–Leone Odd Weibull Flexible-G Family of Distributions with Applications Authors: Chipepa, Fastel; Mahmoud M. Abdelwahab; Charumbira, Wellington Fredrick; Mustafa M. Hasaballah Abstract: The acceptance of generalized distributions has significantly improved over the past two decades. In this paper, we introduce a new generalized distribution: Topp–Leone odd Weibull flexible-G family of distributions (FoD). The new FoD is a combination of two FOD; the Topp–Leone-G and odd Weibull-flexible-G families. The proposed FoD possesses more flexibility compared to the two individual FoD when considered separately. Some selected statistical properties of this new model are derived. Three special cases from the proposed family are considered. The new model exhibits symmetry and long or short tails, and it also addresses various levels of kurtosis. Monte Carlo simulation studies were conducted to verify the consistency of the maximum likelihood estimators. Two real data examples were used as illustrations on the flexibility of the new model in comparison to other competing models. The developed model proved to perform better than all the selected competing models.

2025-01-01T00:00:00Z Chipepa, Fastel Mahmoud M. Abdelwahab Charumbira, Wellington Fredrick Mustafa M. Hasaballah Wellington Fredrick Charumbira Broderick Oluyede Fastel Chipepa Lesego Gabaitiri https://cris.library.msu.ac.zw//handle/11408/6503 2024-12-12T07:01:44Z 2024-10-08T00:00:00Z

Title: The Harris-G power series class of distributions with applications Authors: Wellington Fredrick Charumbira; Broderick Oluyede; Fastel Chipepa; Lesego Gabaitiri Abstract: This study introduces a novel class of distributions (CoD) called the Harris-G power series (H-GPS) CoD. The model is obtained by compounding the Harris-G distribution with the power series distribution (PSD). Some statistical properties including quantile function, linear representation, distribution of order statistics, moments, probability weighted moments and Rényi entropy are developed. Four special cases including the Harris-log-logistic distribution, Harris-log-logistic logarithmic distribution, Harris-Weibull Poisson distribution and the Harris-Weibull logarithmic distribution are presented. Parameter estimation is done using maximum likelihood estimation technique. A simulation study is carried out for the special case of Harris-Weibull Poisson (H-WP) distribution. Finally the Harris-Weibull Poisson is applied to two real datasets to illustrate the usefulness and applicability of the model.

2024-10-08T00:00:00Z Wellington Fredrick Charumbira Broderick Oluyede Fastel Chipepa Lesego Gabaitiri