Statistics and Probability Commons^™

Learning Weibull Loss Severity Models From Truncated And Censored Data, Majed Alkhasha

Graduate Studies Theses and Dissertations 2026

In modern actuarial science and risk management, due to various loss control mechanisms, observed severity losses are typically left-truncated at the deductible, right-censored at the policy limit, and scaled by a pre-specified co-insurance factor. This results in two types of actuarial payment random variables: payment-per-payment (PPP) and payment-per-loss (PPL). To learn ground-up Weibull loss severity models from PPP and PPL sample data, we implement two estimation techniques: Maximum Likelihood Estimation (MLE) and the dynamic Method of Trimmed Moments (MTM). MLE is employed to obtain efficient estimates of the Weibull shape and scale parameters. However, MLE may assign unnecessarily large point …

Time Series Decomposition And Forecasting Of Alzheimer’S Disease Mortality Using A Kolmogorov-Zurbenko Filter, Jack D. Farrell

Electronic Theses & Dissertations (2024 - present)

Alzheimer’s disease mortality has substantially risen in recent history, placing a significant burden on public health infrastructure and highlighting the need for improved analytical methods to better understand mortality data patterns and offer reliable predictions. Time series methods often struggle to balance both accuracy and interpretability, which hinders the ability to gather meaningful insights from time series data. To address these limitations, this study applies the Kolmogorov-Zurbenko (KZ) filter to monthly U.S. Alzheimer’s mortality data spanning from 1999 to 2023 and decomposes the series into long-term trend, seasonal, and noise components on a logarithmic scale. Long-term trend accounts for 86.49% …

A Dataset-Centric Analysis Of Evaluation Protocols In Face Morph Attack Detection, Sheerko R. Hmasalah, Abdulbasit K. Al-Talabani, Aras T. Asaad

Polytechnic Journal

Face morph attack detection (MAD) is often evaluated using datasets collected from diverse sources, created for different purposes, and acquired under varying conditions. This heterogeneity raises questions about how evaluation protocols and dataset characteristics influence reported performance. This work adopts a dataset-centric perspective to analyze the effects of evaluation protocol and dataset composition, including visual quality and morph-to-genuine imbalance, on MAD performance. Experiments are conducted on eight datasets and four morphing techniques using a fixed pipeline evaluated across six backbones, including Vision Transformer (ViT) and five CNN architectures, and ten evaluation scenarios covering homogeneous and heterogeneous cross-morph generalization. Performance is …

Data-Driven Partitioning In Distributed Optimization For Networked Systems, Prosper Azameti

Theses and Dissertations

The convergence behavior of distributed optimal power flow (OPF) depends strongly on how the power network is partitioned into regions. Classical graph-based methods such as METIS are widely used, but they rely mainly on static topological criteria and do not explicitly incorporate operating-point-dependent information that may affect distributed optimization performance. This thesis develops a data-driven partitioning framework for distributed OPF using graph neural networks (GNNs). Each OPF scenario is represented as a graph in which buses are nodes and transmission lines are edges. Node and edge features capture both structural and operational characteristics of the network. Partition prediction is formulated …

Theoretical Analysis Of Filtering And Smoothing Techniques In Stochastic Time Series, Kaosarat Bola Azeez

Theses and Dissertations

Polynomial-preserving linear filters are fundamental tools for smoothing and trend extraction in noisy time series, particularly when the objective is to reduce short-run variation without distorting underlying low-degree structure. This thesis develops a general framework for such filters based on local polynomial approximation and least-squares estimation. In particular, we establish that the resulting estimators can be represented as symmetric linear filters whose weights satisfy moment conditions that ensure exact polynomial reproduction up to a specified degree. Building on this framework, we derive explicit coefficient vectors for several classical smoothing filters, including the Savitzky-Golay filters SG(5,2) and SG(7,3), as well as …

Essays On Accelerated Failure Time Models For Recurrent Event Data, Emmanuel Masavo Djegou

Doctoral Dissertations

Recurrent event data arise in many fields such as medicine, reliability, insurance, and economics, where the same event may occur repeatedly for a subject. Accelerated Failure Time (AFT) models provide an intuitive framework for relating covariates to event times and offer a useful alternative to proportional hazards models, allowing direct prediction of event timing under right censoring. However, existing AFT extensions for recurrent events, such as accelerated gap time (AGT) models, often fail to account for interventions between events and may not capture complex temporal patterns.

In this work, we first propose a class of semiparametric AGT models incorporating an …

Differential Impact Of Admission Type And Clinical Complexity On Diabetes Hospitalization Costs Among African American And Hispanic Patients In Southeastern Virginia, Ismail El Moudden, Asra Amidi, Reem Sharaf-Alddin, Michael C. Bittner, Qi Zhang

Department of Obstetrics & Gynecology Faculty Publications

Background

Diabetes mellitus (DM) imposes substantial healthcare costs with documented disparities among African Americans and Hispanic patients. To inform care delivery and resource allocation, this study identified hospitalization cost predictors among African American and Hispanic patients with diabetes in Southeastern Virginia.

Methods

We analyzed 6,011 hospital discharges from the Virginia Health Information database (2016-2020) for adults aged 18-85 with diabetes. Discharges were classified by Medicare Severity Diagnosis-Related Groups: DM with complications/comorbidities (DCC, n = 3,328), DM with major complications/comorbidities (DMCC, n = 1,518), and DM without major complications/comorbidities (DWO, n = 1,165). Because cost distributions were right-skewed (skewness 3.5-8.24), we …

High Algal Biomass Is Decoupled From Metabolism In The Gallatin River, Cora Mae Steinbach

Graduate Student Theses, Dissertations, & Professional Papers

Assessing eutrophication in rivers is difficult compared to lakes and coastal waters, because most algal biomass occurs on the riverbed and flows interact and co-vary with production (Biggs and Close, 1989; Bernhardt et al., 2018). Riverine eutrophication is typically assessed using algal biomass and water column nutrients (U.S. Environmental Protection Agency, 2000), but biomass is highly variable and labor-intensive to measure, while nutrient concentrations often underestimate enrichment due to rapid biological uptake (Dodds and Smith, 2016). Reach-scale river metabolism can help evaluate long-term functional change in rivers recovering from nutrient enrichment (Arroita et al., 2019; Jankowski et al., 2021; Diamond …

Seemingly Unrelated Exponetiated Exponential Geometric Regression Model, Oluwaseun Michael Famoni, Bamidele Mustapha Oseni

Al-Bahir

In the class of seemingly unrelated regression models, the dispersion nature of the dependent variable can greatly impact the efficiency and reliability of the parameter estimates for the model. Despite this, the seemingly unrelated Poisson regression model and seemingly unrelated negative binomial model are two most commonly used count data models for these class of regression models. This study introduces the seemingly unrelated exponentiated exponential geometric regression (SUEEGR) for modelling count data which might be equi-, under, or over-dispersed. Parameters estimation for the model was carried out using the method of maximum likelihood. A simulation study was carried out to …

Comparing The Effectiveness Of Eggshell Spectra From Laser-Induced Break-Down Spectroscopy And Near-Infrared Spectroscopy Using Principal Compo-Nent Analysis To Determine The Authenticity Of Organic Eggs, Ahmad Qusthalani, Rara Mitaphonna, Muliadi Ramli, Rajibussalim Rajibussalim, Kurnia Lahna, Nasrullah Zaini, Nasrullah Idris

Makara Journal of Science

This study aimed to explore the potential of modern spectroscopy in the authentication of organic and non-organic chicken eggs using near-infrared spectroscopy (NIRS) and laser-induced breakdown spectroscopy (LIBS) spectra. A total of 175 eggs were analyzed, which were grouped into seven categories based on the source of feed given: 100% organic, 100% non-organic, 75% organic, 75% non-organic, 50% organic, free-range chickens, and eggs obtained from the local traditional market. Each group consisted of 25 eggs. NIRS spectra were recorded in the wavelength range of 350–2500 nm, whereas LIBS spectra were recorded in the range of 200–900 nm. A total of …

(R2141) Analysis Of Map^I_1 , Ph^(Oa)_2 / Ph^I_1 , Ph^O_2 / 1 Retrial Inventory Queue With Two Way Communication, (S, S) Replenishment Policy, Feedback, Bernoulli Vacation And Impatient Customers, G. Ayyappan, V. Ganesan

Applications and Applied Mathematics: An International Journal (AAM)

This work discusses about the topic as the two-way communication retrial inventory queue model, the (s, S) replenishment policy, immediate feedback, Bernoulli vacations, and impatient customers. The assumption we make is that arrivals follow a Markovian arrival process, and the server provides phase type services. When the server is idle and there is a positive inventory, an arriving customer immediately receives service. If not, arriving customers goes to orbit with infinite capacity. Only in the account of positive inventory the server renders rapid feedback for incoming call arrivals, otherwise customer departs. Outgoing calls will only be made by the server …

(R2152) New Bivariate Type-2 Gumbel Distribution Based On The Farlie-Gumbel-Morgenstern Copula: Properties And Its Application In Survival Analysis, Muneeb Javed, Said Farooq Shah, Muhammad Osama, Muhammad Atif, Muhammad Farooq

Applications and Applied Mathematics: An International Journal (AAM)

We introduce a new bivariate probability distribution, termed the Bivariate FGM Type-2 Gumbel Distribution, constructed by combining the Farlie–Gumbel–Morgenstern (FGM) copula with the Type-2 Gumbel marginal distributions. This proposed distribution provides a flexible framework for modeling bivariate data and offers a viable alternative to several existing bivariate distributions, especially in scenarios where capturing dependence between variables is crucial. The theoretical properties of the distribution are thoroughly explored. We derive the marginal and conditional distributions, conditional expectations, moment generating function, and product moments. Procedures for random number generation from the distribution are discussed. Reliability-based characteristics, such as the survival function and …

Shaking Table Test And Numerical Simulation Of Seismic Response Characteristics Of Rock Slope With Muddy Interlayer, Duan Chenggang, Fang Yanlin, Tian Yeqing, Zhou Zhijun

Journal of China & Foreign Highway

In order to study the seismic macroscopic failure process and dynamic response characteristics of rock slope with muddy interlayer and reveal the influence of muddy interlayer on slope stability,a similar slope model with concave and convex slope types was designed,and shaking table test was carried out;finite element analysis was used for numerical modeling analysis,and the results obtained by the two models were compared.The results show that:① The macroscopic deformation and failure process of the model slope is divided into three stages.Muddy interlayer dislocates,and cracks occur;mud interlayer slips,and cracks expand;slope collapses;② The seismic load has a decisive influence on the stability …

Effect Of Lithium Slag Dosage On Strength And Dry Shrinkage Properties Of Cement Stabilized Recycled Macadam, Zhao Ziyu, Gan Xianyong

Journal of China & Foreign Highway

To improve the mechanical properties and dry shrinkage properties of cement stabilized bases formed by cold in-place recycling of cement concrete pavements,lithium slag was mixed into the recycled mixture in mass ratios of 0%,6%,9%,and 12%.The effects of lithium slag dosage on the mechanical,dry shrinkage,and water stability properties of the recycled base were analyzed through the unconfined compressive strength,splitting,dry shrinkage,and water stability tests,and the mechanism underlying the improving effect of lithium slag on the cement stabilized base formed by cold in-place recycling of the cement concrete pavement was analyzed by X-ray diffraction (XRD ) and scanning electron microscopy (SEM ).The results …

Optimization Of Infill Concrete Dimension In Composite Girder Box Based On Igrnn, Wang Yafeng, Liu Jian, Ke Hongjun

Journal of China & Foreign Highway

The mechanical performance of the negative bending moment zone of steel-concrete composite continuous girders has always been a focus of attention in bridge engineering.Existing research mainly proposes improvement measures for the tension of concrete bridge decks,while paying little attention to the common phenomenon of steel girders bearing pressure.The steel girders in steel-concrete composite girders,especially the steel bottom plate in the negative bending moment area of the pier top,bear the highest compressive stress of the entire bridge.Therefore,by taking a steel-concrete composite girder bridge in Zhejiang Province as the engineering background,it is proposed to partially fill the interior of the box girder …

Research On Cable Force Optimization Of Long-Span Cable-Stayed Bridges Based On Rbfnn+Improved Parti Cle Swarm Optimization Algorithm, Deng Da, He Bowen, Liu Guokun

Journal of China & Foreign Highway

In view of the cable force optimization problem of long-span cable-stayed bridges,a cable force optimization method considering the reliability index of stay cables was proposed based on the response surface fitted by the radial basis function neural network (RBFNN ).The RBFNN-based response surface model for solving the reliability index was established by fitting the structural implicit function through RBFNN training.The improved particle swarm optimization algorithm was used to search for the optimal solution of the cable force optimization model considering the reliability index.The research results show that RBFNN can accurately predict the structural responses and fit the structural implicit performance …

Design Optimization And Experimental Study Of Cfrp Plate Anchorage With Clip-Extension Type, Qi Yijia, Xiao Dan, Wang Zhongqiang

Journal of China & Foreign Highway

Existing anchorage is prone to damaging the carbon-fiber reinforced polymer (CFRP ) plate due to the “notch effect ” and uneven distribution of clamping stress.This study proposed a new clip-extension type anchorage for the CFRP plate.This design utilized the ductility of steel for stress diffusion and guided the compressive stress zone in the CFRP plate away from the notched end,realizing a smooth transition of the clamping force of the CFRP plate at the clip port and effectively reducing the “notch effect ”.The design also reduced the strain difference between the carbon fibers,resulting in a more synchronized lateral deformation of the …

Research And Applicat Ion Of Ultra Large-Scale Consolidated Under-Reamed Drilled Shaft Technology Under Special Environmental And Geological Conditions, Ding Yi, Yu Kun, Shi Haiyang, Pei Xiaofeng, Zhu Bo

Journal of China & Foreign Highway

This article aims to add ress the poor economic efficiency of large-diameter and ultra-long piles,the high risk of hole collapse in thick sandy soil,and the limited space across the canal faced by the Bridge over Yellow River Diversion to Qindao Canal on Zhanhua ‒ Linyi Expressway.According to the comparison of conventional drilled cast-in-place piles with combined pile-end and pile-side post-grouting,the industry ’s under-reamed drilled shaft foundation with the largest disc diameter (4.5 m) and the largest single-pile volume (456 m3) was proposed and designed.At the same time,supporting devices such as three-arm rotary cutting drill bits and long arm borehole diameter …

Analysis Of Influence Of Internal Erosion On Deformation Of Subway Station Structure, Qin Tianxin, Wang Chen, Tan Xuyan, Wei Shengming, Liang Fayun

Journal of China & Foreign Highway

Under the long-term effects of disasters such as rainstorms and floods,the soil layer around subway stations may be affected by internal erosion,threatening the structural safety of urban subway stations.To explore the influence of internal erosion on subway station structures,this study conducted isotropic consolidation and triaxial compression tests on gap-graded sand soil.Eroded soil specimens were simulated by adjusting the fine particle content to explore the pattern of variations in physical and mechanical properties caused by internal erosion.Results indicate that internal erosion alters the stress-strain relationship of gap-graded sand soil,increasing compressibility,decreasing shear strength,and weakening dilatancy.Drucker-Prager (DP) cap model parameters for eroded sand …

Evaluation Method For Nighttime Visual Space Improvement On Mountain Roads, Zhao Yan, Chen Yanli, Chen Jiale

Journal of China & Foreign Highway

To address issues such as poor visual guidance,narrow field of view,and short sight distance during nighttime driving on mountain roads,this study proposed a visual space enhancement evaluation method applicable to mountainous roads at night.By integrating active and passive traffic safety facilities,a visual space enhancement strategy adapted to the nighttime environment of mountain roads was proposed.A multidimensional evaluation indicator for visual space was established based on co-simulation.The effectiveness of the strategy was verified from the perspectives of visual space expansion and driving safety improvement by taking a trunk highway in the Qinling mountainous region as a case study.The results show that …