Statistics and Probability Commons^™

Learning Latent Causal Dynamics, Weiran Yao, Guangyi Chen, Kun Zhang

Machine Learning Faculty Publications

One critical challenge of time-series modeling is how to learn and quickly correct the model under unknown distribution shifts. In this work, we propose a principled framework, called LiLY, to first recover time-delayed latent causal variables and identify their relations from measured temporal data under different distribution shifts. The correction step is then formulated as learning the low-dimensional change factors with a few samples from the new environment, leveraging the identified causal structure. Specifically, the framework factorizes unknown distribution shifts into transition distribution changes caused by fixed dynamics and time-varying latent causal relations, and by global changes in observation. We …

Diet Quality Scores And Cardiometabolic Risk Factors In Mexican Children And Adolescents: A Longitudinal Analysis, Abeer Ali Aljahdali, Karen E. Peterson, Alejandra Cantoral, Edward Ruiz-Narvaez, Martha M. Tellez-Rojo, Hyungjin Myra Kim, James R. Hébert Scd, Michael David Wirth Msph, Phd, Face, Libni A. Torres-Olascoaga, Nitin Shivappa Mbbs, Mph, Ph.D., Ana Baylin

Faculty Publications

There is limited evidence for the effects of diet on cardiometabolic profiles during the pubertal transition. We collected repeated measures of diet quality and cardiometabolic risk factors among Mexican youth. This analysis included 574 offspring of the Early Life Exposure in Mexico to Environmental Toxicants (ELEMENT) birth cohort followed up to three time points. Dietary Approaches to Stop Hypertension (DASH), alternate Mediterranean Diet (aMedDiet), and Children’s Dietary Inflammatory Index (C-DII^TM) scores were computed from food frequency questionnaires. Higher DASH and aMedDiet scores reflect a higher diet quality, and lower C-DII scores reflect an anti-inflammatory diet. Cardiometabolic risk factors …

Patients With Obesity And A History Of Metformin Treatment Have Lower Influenza Mortality: A Retrospective Cohort Study, Tammy H. Cummings, Joseph Magagnoli Ph.D., Ms, James W. Hardin, S. Scott Sutton

Faculty Publications

Background: Obesity is a risk factor for the development of influenza by leading to a chronic inflammatory state and T-cell dysfunction. Based upon preclinical research, metformin has influenza activity by restoring T-cell function and improving the immune response. Objective: We aimed to evaluate the potential drug repurposing of metformin for the management of influenza among patients with obesity utilizing national claims data in an electronic health record database. Methods: The VA Informatics and Computing Infrastructure (VINCI) was utilized to obtain individual-level information on demographics, administrative claims, and pharmacy dispensation. A cohort was created among individuals with laboratory confirmed diagnosis of …

How The Number Line Can Be Used To Promote Students' Understanding Of The Normal Distribution, Danri H. Delport

Numeracy

A strong foundation in early number concepts is crucial for students’ future success in statistics. Despite its importance in statistics, many first-year students struggle to comprehend the normal distribution due to a lack of basic number sense. Students get confused about the order and magnitude of negative z-scores on a standard normal curve or when problems about normally distributed random variables are presented in word questions which involve phrases that indicate inequalities. As a result, students shade wrong areas on the bell-shaped curve when they have to calculate probabilities for normally distributed variables. Visual representations such as the number …

Adverse Events Reporting Of Clinical Trials In Exercise Oncology Research (Advance): Protocol For A Scoping Review, Hao Luo, Oliver Schumacher, Daniel A. Galvão, Robert U. Newton, Dennis R. Taaffe

Research outputs 2022 to 2026

Introduction: Adequate, transparent, and consistent reporting of adverse events (AEs) in exercise oncology trials is critical to assess the safety of exercise interventions for people following a cancer diagnosis. However, there is little understanding of how AEs are reported in exercise oncology trials. Thus, we propose to conduct a scoping review to summarise and evaluate current practice of reporting of AEs in published exercise oncology trials with further exploration of factors associated with inadequate reporting of AEs. The study findings will serve to inform the need for future research on standardisation of the definition, collection, and reporting of AEs for …

Diet Quality And Dietary Inflammatory Index Score Among Women’S Cancer Survivors, Sibylle Kranz, Faten Hasan, Erin Kennedy, Jamie Zoellner, Kristin A. Guertin, Nitin Shivappa Mbbs, Mph, Ph.D., James R. Hébert, Roger Anderson, Wendy Cohn

Faculty Publications

The purpose of this study was to investigate Healthy Eating Index 2015 (HEI-2015) and Energy-Adjusted Dietary Inflammatory Index (E-DIITM) scores in women's cancer survivors and to examine socio-economic (SES) characteristics associated with these two diet indices. In this cross-sectional study, survivors of women's cancers completed a demographic questionnaire and up to three 24-h dietary recalls. HEI-2015 and E-DII scores were calculated from average intakes. One-way ANOVA was used to examine the association of various demographic factors on HEI-2015 and E-DII scores. Pearson Correlation was used to calculate the correlation between the two scores. The average HEI-2015 score was 55.0 +/- …

Session 13: On Statistical Estimates Of The Inverted Kumaraswamy Distribution Under Adaptive Type-I Progressive Hybrid Censoring, Qingqing Li, Yuhlong Lio

SDSU Data Science Symposium

The probability distribution modeling is investigated via maximum likelihood estimation method based on adaptive type-I progressively hybrid censored samples from the inverted Kumaraswamy distribution. The point estimates of model parameters, reliability, hazard rate and quantile are obtained and confidence intervals are also developed by using asymptotic distribution as well as bootstrap method. Monte Carlo simulation has been performed to evaluate the accuracy of estimations. Finally, a real data set is given for the application illustration.

An Alpha-Based Prescreening Methodology For A Common But Unknown Source Likelihood Ratio With Different Subpopulation Structures, Dylan Borchert, Semhar Michael, Christopher Saunders, Andrew Simpson

SDSU Data Science Symposium

Prescreening is a commonly used methodology in which the forensic examiner includes sources from the background population that meet a certain degree of similarity to the given piece of evidence. The goal of prescreening is to find the sources closest to the given piece of evidence in an alternative source population for further analysis. This paper discusses the behavior of an $\alpha-$based prescreening methodology in the form of a Hotelling $T^2$ test on the background population for a common but unknown source likelihood ratio. An extensive simulation study with synthetic and real data were conducted. We find that prescreening helps …

Identifying Subpopulations Of A Hierarchical Structured Data Using A Semi-Supervised Mixture Modeling Approach, Andrew Simpson, Semhar Michael, Christopher Saunders, Dylan Borchert

SDSU Data Science Symposium

The field of forensic statistics offers a unique hierarchical data structure in which a population is composed of several subpopulations of sources and a sample is collected from each source. This subpopulation structure creates a hierarchical layer. We propose using a semi-supervised mixture modeling approach to model the subpopulation structure which leverages the fact that we know the collection of samples came from the same, yet unknown, source. A simulation study based on a famous glass data was conducted and shows this method performs better than other unsupervised approaches which have been previously used in practice.

Session 5: Equipment Finance Credit Risk Modeling - A Case Study In Creative Model Development & Nimble Data Engineering, Edward Krueger, Landon Thompson, Josh Moore

SDSU Data Science Symposium

This presentation will focus first on providing an overview of Channel and the Risk Analytics team that performed this case study. Given that context, we’ll then dive into our approach for building the modeling development data set, techniques and tools used to develop and implement the model into a production environment, and some of the challenges faced upon launch. Then, the presentation will pivot to the data engineering pipeline. During this portion, we will explore the application process and what happens to the data we collect. This will include how we extract & store the data along with how it …

Angiotensin Blockade Therapy And Survival In Pancreatic Cancer: A Population Study, Scott W Keith, Vittorio Maio, Hwyda A Arafat, Matthew Alcusky, Thomas Karagiannis, Carol Rabinowitz, Harish Lavu, Daniel Z. Louis

College of Population Health Faculty Papers

Background: Pancreatic cancer (PC) is one of the most aggressive and challenging cancer types to effectively treat, ranking as the fourth-leading cause of cancer death in the United States. We investigated if exposures to angiotensin II receptor blockers (ARBs) or angiotensin I converting enzyme (ACE) inhibitors after PC diagnosis are associated with survival.

Methods: PC patients were identified by ICD-9 diagnosis and procedure codes among the 3.7 million adults living in the Emilia-Romagna Region from their administrative health care database containing patient data on demographics, hospital discharges, all-cause mortality, and outpatient pharmacy prescriptions. Cox modeling estimated covariate-adjusted mortality hazard ratios …

Transmodel: An R Package For Linear Transformation Model With Censored Data, Jie Zhou, Jiajia Zhang Ph.D.

Faculty Publications

Linear transformation models, including the proportional hazards model and proportional odds model, under right censoring were discussed by Chen, Jin, and Ying (2002). The asymptotic variance of the estimator they proposed has a closed form and can be obtained easily by plug-in rules, which improves the computational efficiency. We develop an R package TransModel based on Chen's approach. The detailed usage of the package is discussed, and the function is applied to the Veterans' Administration lung cancer data.

Comparison Of Human Urinary Exosomes Isolated Via Ultracentrifugation Alone Versus Ultracentrifugation Followed By Sec Column-Purification, Kun Huang, Sudha Garimella, Alyssa Clay-Gilmour, Lucia Vojtech, Bridget Armstrong, Madison Bessonny, Alexis Stamatikos

Faculty Publications

Chronic kidney disease is a progressive, incurable condition that involves a gradual loss of kidney function. While there are no non-invasive biomarkers available to determine whether individuals are susceptible to developing chronic kidney disease, small RNAs within urinary exosomes have recently emerged as a potential candidate to use for assessing renal function. Ultracentrifugation is the gold standard for urinary exosome isolation. However, extravesicular small RNA contamination can occur when isolating exosomes from biological fluids using ultracentrifugation, which may lead to misidentifying the presence of certain small RNA species in human urinary exosomes. Therefore, we characterized human urinary exosomal preparations isolated …

Periodicity On Isolated Time Scales, Martin Bohner, Jaqueline Mesquita, Sabrina Streipert

Mathematics and Statistics Faculty Research & Creative Works

In this work, we formulate the definition of periodicity for functions defined on isolated time scales. The introduced definition is consistent with the known formulations in the discrete and quantum calculus settings. Using the definition of periodicity, we discuss the existence and uniqueness of periodic solutions to a family of linear dynamic equations on isolated time scales. Examples in quantum calculus and for mixed isolated time scales are presented.

On Inclusions With Monotone-Type Mappings In Nonreflexive Banach Spaces, Vy Khoi Le

Mathematics and Statistics Faculty Research & Creative Works

We are concerned in this article with the existence of solutions to inclusions containing generalized pseudomonotone perturbations of maximal monotone mappings in general Banach spaces. Our approach is based on a truncation–regularization technique and an extension of the Moreau–Yosida–Brezis–Crandall–Pazy regularization for maximal monotone mappings in general Banach spaces. We also consider some applications to multivalued variational inequalities containing elliptic operators with rapidly growing coefficients in Orlicz–Sobolev spaces.

Marginal Proportional Hazards Models For Clustered Interval-Censored Data With Time-Dependent Covariates, Kaitlyn Cook, Wenbin Lu, Rui Wang

Harvard University Biostatistics Working Paper Series

The Botswana Combination Prevention Project was a cluster-randomized HIV prevention trial whose follow-up period coincided with Botswana’s national adoption of a universal test-and-treat strategy for HIV management. Of interest is whether, and to what extent, this change in policy (i) modified the observed preventative effects of the study intervention and (ii) was associated with a reduction in the population-level incidence of HIV in Botswana. To address these questions, we propose a stratified proportional hazards model for clustered interval-censored data with time-dependent covariates and develop a composite expectation maximization algorithm that facilitates estimation of model parameters without placing parametric assumptions on …

A Multigrid Multilevel Monte Carlo Method For Stokes–Darcy Model With Random Hydraulic Conductivity And Beavers–Joseph Condition, Zhipeng Yang, Ju Ming, Changxin Qiu, Maojun Li, Xiaoming He

Mathematics and Statistics Faculty Research & Creative Works

A multigrid multilevel Monte Carlo (MGMLMC) method is developed for the stochastic Stokes–Darcy interface model with random hydraulic conductivity both in the porous media domain and on the interface. Three interface conditions with randomness are considered on the interface between Stokes and Darcy equations, especially the Beavers–Joesph interface condition with random hydraulic conductivity. Because the randomness through the interface affects the flow in the Stokes domain, we investigate the coupled stochastic Stokes–Darcy model to improve the fidelity. Under suitable assumptions on the random coefficient, we prove the existence and uniqueness of the weak solution of the variational form. To construct …

Probability Models With Discrete And Continuous Parts, James E. Marengo, David L. Farnsworth

Articles

In mathematical statistics courses, students learn that the quadratic function E ((X – x )-squared) is minimized when x is the mean of the random variable X, and that the graphs of this function for any two distributions of X are simply translates of each other. We focus on the problem of minimizing the function defined by y ( x) = E ( IX – xI-squared ) in the context of mixtures of probability distributions of the discrete, absolutely continuous, and singular continuous types. This problem is important, for example, in Bayesian statistics, when one attempts to compute the decision …

Towards Statistical Best Practices For Gender And Sex Data, Suzanne Thornton, D. Roy, S. Parry, D. Lalonde, W. Martinez, R. Ellis, D. Corliss

Mathematics & Statistics Faculty Works

Suzanne Thornton, Dooti Roy, Stephen Parry, Donna LaLonde, Wendy Martinez, Renee Ellis and David Corliss call for a more inclusive – and informative – approach to collecting data on human gender and sex.

Liquidity Commonality With Factor Models, Ernesto Garcia Iii

Dissertations, Theses, and Capstone Projects

Market microstructure research has recently devoted attention to a phenomenon called commonality in liquidity. In this dissertation, I will analyze commonality in liquidity using a novel factor model approach and a generalized definition of commonality in liquidity. This analysis will show that commonality in liquidity is rarely a marketwide phenomenon and is mostly restricted to stocks with a large market capitalization. Additionally, commonality in liquidity is a very recent phenomenon whose appearance coincides with a rise in passive investing after the Dotcom Bubble burst and, more so, after the 2008 Financial Crisis. I will present evidence that suggests commonality in …