Thamer Manshi

Dr. Thamer Manshi


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 September 2025 in Stats
Verified
Journal Article
Open access
PDF file
ASAmmar M. Sarhan
Ammar M. Sarhan
TMThamer Manshi
Thamer Manshi
MEMohamed E.Sobh
Mohamed E.Sobh
This paper introduces the Unit-Modified Weibull (UMW) distribution, a novel probability model defined on the unit interval (0, 1). We derive its key statistical properties and estimate its parameters using the maximum likelihood method. The performance of the estimators is assessed via a simulation study based on mean squared error, coverage probability, and average confidence interval length. To evaluate the practical utility of the model, we analyze three real-world data sets. Both parametric and nonparametric goodness-of-fit techniques are employed to compare the UMW distribution with several well-established competing models. In addition, nonparametric diagnostic tools such as total time on test transform plots and violin plots are used to explore the data’s behavior and assess the adequacy of the proposed model. Results indicate that the UMW distribution offers a competitive and flexible alternative for modeling bounded data.

28 December 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
ASAmmar M. Sarhan
Ammar M. Sarhan
Ahlam H. TolbaAhlam H. Tolba
Ahlam H. Tolba
DRdina ahmed ramadan
dina ahmed ramadan
TMThamer Manshi
Thamer Manshi
This paper introduces a novel bivariate distribution, referred to as the Bivariate Burr XII Inverse Weibull (BBXII-IW) distribution, constructed via the Marshall–Olkin approach from the univariate Burr XII Inverse Weibull (BXII-IW) distribution. The proposed BBXII-IW model provides a flexible framework for modeling dependent bivariate data, including competing risk scenarios. The key statistical properties of the distribution are derived, and parameter estimation is conducted using the maximum likelihood method. The model’s performance is evaluated using two types of real-world datasets: (1) bivariate data and (2) dependent competing risk data related to diabetic retinopathy. The results demonstrate that the BBXII-IW distribution offers an improved fit compared to existing models, highlighting its flexibility and practical relevance in modeling complex dependent structures.

21 January 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
TMThamer Manshi
Thamer Manshi
ASAmmar M. Sarhan
Ammar M. Sarhan
MEMohamed E.Sobh
Mohamed E.Sobh
Developing flexible lifetime distributions is essential for accurately modeling reliability and lifetime data across various scientific and engineering contexts. In this work, we introduce a new three-parameter lifetime distribution, which extends the well-known two-parameter Sarhan–Tadj–Hamilton model. We derive and discuss several of its important theoretical properties, including the reliability characteristics and moments. The parameter estimation is carried out using both maximum likelihood and Bayesian approaches, providing a comprehensive comparison of inferential techniques. To further examine the efficiency and robustness of the proposed estimators, a detailed Monte Carlo simulation study is conducted under different sample sizes and parameter settings. The practical usefulness of the distribution is illustrated through its application to three real-world datasets, namely cancer and COVID-19 data, where it demonstrates superior fit and flexibility compared to existing and nested lifetime models. These findings highlight the potential of the proposed model as a valuable addition to the toolbox of applied statisticians and reliability practitioners.

1 January 2026 in AIMS Mathematics
Verified
Journal Article
Open access
PDF file
TMThamer Manshi
Thamer Manshi
In this paper, a semi-parametric distributional inference framework was developed for mean residual life analysis when the inspection age is latent, random, or only indirectly specified through a stochastic monitoring mechanism. Classical mean residual life methods evaluate the expected remaining lifetime at a fixed and fully observed age, an assumption that may be restrictive in reliability, survival, and predictive-maintenance studies where inspection times are irregular, missing, or governed by external monitoring policies. For a lifetime variable T and an independent random inspection age X, the proposed framework targeted the conditional residual-life functional $ (T-X|T\;>X) $, thereby incorporating uncertainty in the observation process directly into lifetime-distribution analysis. The lifetime distribution was estimated nonparametrically, whereas the latent inspection-age distribution was modeled parametrically, leading to a flexible and implementable inference procedure for complete and right-censored lifetime data. Under the exponential inspection model, explicit finite-sum representations were derived, avoiding numerical double integration and enabling direct computation from ordered lifetime observations and Kaplan-Meier survival estimates. The theoretical development established strong consistency and derived the asymptotic normality of the complete-data estimator. A plug-in estimator of the asymptotic variance was also introduced, yielding analytically justified standard errors and large-sample confidence intervals. Simulation studies under Weibull and gamma lifetime distributions demonstrated coherent finite-sample performance across aging regimes, inspection intensities, sample sizes, and censoring proportions. A fixed-age benchmark comparison further showed that replacing the random inspection age by its mean may conceal important distributional effects of monitoring uncertainty. Real-data analyses using kidney catheter survival data, aircraft air-conditioning failure times, and NASA C-MAPSS turbofan degradation lifetimes illustrated the practical value of the proposed methodology in biomedical, engineering, and predictive-maintenance applications. The proposed approach therefore contributes to statistical distribution theory and its applications by extending classical residual-life inference to modern lifetime-data settings in which observation ages are unavailable, irregularly recorded, or operationally uncertain.

1 January 2026 in AIMS Mathematics
Verified
Journal Article
Open access
PDF file
TMThamer Manshi
Thamer Manshi
MAMaha Al-Mutairi
Maha Al-Mutairi
Replacing heterogeneous dependent component models with tractable homogeneous surrogates while preserving system-level stochastic comparisons is a recurring problem in reliability analysis. Existing mean-based results typically fix the surrogate parameter and do not identify the generator-dependent power-mean boundary for universal validity. In this paper, we developed a power-mean homogenization framework for parallel and series systems with proportional hazard rate (PHR) margins under Archimedean dependence. For parallel systems whose generator was valid in every dimension, we established an exact necessary-and-sufficient criterion: For every system size, every positive PHR parameter vector, and every non-degenerate baseline, the heterogeneous system dominated its homogeneous power-mean surrogate in the usual stochastic order if and only if a generator-induced one-variable transform was convex. The criterion yielded an exact critical power index and a constructive two-component counterexample below the admissible region. A relative-curvature condition characterized a dimension-free sufficient Jensen mechanism. For the Gumbel, Clayton, Ali-Mikhail-Haq, and Joe families, the exact and curvature-based criteria produced the same admissible sets over the studied nonzero power-index range with absolute value at most one. Strictness and equality conditions and a second-order local expansion quantified the heterogeneity gain over the arithmetic-mean benchmark. Complementary stochastic comparisons were established for series systems under appropriate convexity assumptions. Under decreasing-failure-rate baselines and additional generator-shape conditions, both system architectures admitted dispersive-order extensions; these results were sufficient rather than exact. The framework provided a rigorous basis for selecting homogeneous PHR benchmarks and comparing dependent heterogeneous systems.