Statistical Methodology Commons^™

Generalized Matrix Decomposition Regression: Estimation And Inference For Two-Way Structured Data, Yue Wang, Ali Shojaie, Tim Randolph, Jing Ma

UW Biostatistics Working Paper Series

Analysis of two-way structured data, i.e., data with structures among both variables and samples, is becoming increasingly common in ecology, biology and neuro-science. Classical dimension-reduction tools, such as the singular value decomposition (SVD), may perform poorly for two-way structured data. The generalized matrix decomposition (GMD, Allen et al., 2014) extends the SVD to two-way structured data and thus constructs singular vectors that account for both structures. While the GMD is a useful dimension-reduction tool for exploratory analysis of two-way structured data, it is unsupervised and cannot be used to assess the association between such data and an outcome of interest. …

Inference Of Heterogeneity In Meta-Analysis Of Rare Binary Events And Rss-Structured Cluster Randomized Studies, Chiyu Zhang

Statistical Science Theses and Dissertations

This dissertation contains two topics: (1) A Comparative Study of Statistical Methods for Quantifying and Testing Between-study Heterogeneity in Meta-analysis with Focus on Rare Binary Events; (2) Estimation of Variances in Cluster Randomized Designs Using Ranked Set Sampling.

Meta-analysis, the statistical procedure for combining results from multiple studies, has been widely used in medical research to evaluate intervention efficacy and safety. In many practical situations, the variation of treatment effects among the collected studies, often measured by the heterogeneity parameter, may exist and can greatly affect the inference about effect sizes. Comparative studies have been done for only one or …

Statistical Inference For Networks Of High-Dimensional Point Processes, Xu Wang, Mladen Kolar, Ali Shojaie

UW Biostatistics Working Paper Series

Fueled in part by recent applications in neuroscience, high-dimensional Hawkes process have become a popular tool for modeling the network of interactions among multivariate point process data. While evaluating the uncertainty of the network estimates is critical in scientific applications, existing methodological and theoretical work have only focused on estimation. To bridge this gap, this paper proposes a high-dimensional statistical inference procedure with theoretical guarantees for multivariate Hawkes process. Key to this inference procedure is a new concentration inequality on the first- and second-order statistics for integrated stochastic processes, which summarizes the entire history of the process. We apply this …

Evaluation Of Modern Missing Data Handling Methods For Coefficient Alpha, Katerina Matysova

College of Education and Human Sciences: Dissertations, Theses, and Student Research

When assessing a certain characteristic or trait using a multiple item measure, quality of that measure can be assessed by examining the reliability. To avoid multiple time points, reliability can be represented by internal consistency, which is most commonly calculated using Cronbach’s coefficient alpha. Almost every time human participants are involved in research, there is missing data involved. Missing data means that even though complete data were expected to be collected, some data are missing. Missing data can follow different patterns as well as be the result of different mechanisms. One traditional way to deal with missing data is listwise …

Communications And Methodologies In Crime Geography: Contemporary Approaches To Disseminating Criminal Incidence And Research, Mitchell Ogden

Electronic Theses and Dissertations

Many tools exist to assist law enforcement agencies in mitigating criminal activity. For centuries, academics used statistics in the study of crime and criminals, and more recently, police departments make use of spatial statistics and geographic information systems in that pursuit. Clustering and hot spot methods of analysis are popular in this application for their relative simplicity of interpretation and ease of process. With recent advancements in geospatial technology, it is easier than ever to publicly share data through visual communication tools like web applications and dashboards. Sharing data and results of analyses boosts transparency and the public image of …

Optimal Design For A Causal Structure, Zaher Kmail

Department of Statistics: Dissertations, Theses, and Student Research

Linear models and mixed models are important statistical tools. But in many natural phenomena, there is more than one endogenous variable involved and these variables are related in a sophisticated way. Structural Equation Modeling (SEM) is often used to model the complex relationships between the endogenous and exogenous variables. It was first implemented in research to estimate the strength and direction of direct and indirect effects among variables and to measure the relative magnitude of each causal factor.

Historically, traditional optimal design theory focuses on univariate linear, nonlinear, and mixed models. There is no current literature on the subject of …

Effect Of Cross-Validation On The Output Of Multiple Testing Procedures, Josh Dallas Price

Graduate Theses and Dissertations

High dimensional data with sparsity is routinely observed in many scientific disciplines. Filtering out the signals embedded in noise is a canonical problem in such situations requiring multiple testing. The Benjamini--Hochberg procedure using False Discovery Rate control is the gold standard in large scale multiple testing. In Majumder et al. (2009) an internally cross-validated form of the procedure is used to avoid a costly replicate study and the complications that arise from population selection in such studies (i.e. extraneous variables). I implement this procedure and run extensive simulation studies under increasing levels of dependence among parameters and different data generating …

Taking Multiple Regression Analysis To Task: A Review Of Mindware: Tools For Smart Thinking, By Richard Nisbett (2015), Jason Makansi

Numeracy

Richard Nisbett. 2015. Mindware: Tools for Smart Thinking.(New York, NY: Farrar, Strauss, and Giroux). 336 pp. ISBN: 9780374536244

Nisbett, a psychologist, may not achieve his stated goal of teaching readers to “effortlessly” extend their common sense when it comes to quantitative analysis applied to everyday issues, but his critique of multiple regression analysis (MRA) in the middle chapters of Mindware is worth attention from, and contemplation by, the QL/QR and Numeracy community. While in at least one other source, Nisbett’s critique has been called a “crusade” against MRA, what he really advocates is that it not be used as …

Using Meta-Analysis To Assess Affective Outcomes In A Multi-Course Qr Module Intervention, James Friedrich, Kelley D. Strawn

Numeracy

When quantitative reasoning(QR) interventions share a common hypothesis or goal, a promising approach for evaluation involves integrating separate analyses through the use of meta-analysis. This paper reports an assessment of a module-based QR intervention distributed across 20 courses at a single institution. Topics and participating courses were diverse, including arts & humanities, quantitative behavioral sciences, and natural sciences & mathematics groupings, but all addressed the shared affective goals of reducing student QR self-doubt and increasing appreciation for QR value and utility. With a local framework to guide module development, we assess these outcomes using reliable self-report measures in a pre-post …

Interpreting Patient Reported Outcomes In Orthopaedic Surgery: A Systematic Review, Shgufta Docter, Zina Fathalla, Michael Lukacs, Michaela Khan, Morgan Jennings, Shu-Hsuan Liu, Dong Zi, Dianne Bryant

Western Research Forum

Background: Reporting methods of patient reported outcome measures (PROMs) vary in orthopaedic surgery literature. While most studies report statistical significance, the interpretation of results would be improved if authors reported confidence intervals (CIs), the minimally clinically important difference (MCID), and number needed to treat (NNT).

Objective: To assess the quality and interpretability of reporting the results of PROMs. To evaluate reporting, we will assess the proportion of studies that reported (1) 95% CIs, (2) MCID, and (3) NNT. To evaluate interpretation, we will assess the proportion of studies that discussed results using the MCID or the effect sizes and how …

Modelling Weighted Signed Networks, Alberto Caimo, Isabella Gollini

Conference papers

In this paper we introduce a new modelling approach to analyse weighted signed networks by assuming that their generative process consists of two models: the interaction model which describes the overall connectivity structure of the relations in the network without taking into account neither the weight nor the sign of the dyadic relations; and the conditional weighted signed network model describes how the edge signed weights form given the interaction structure. We then show how this modelling approach can facilitate the interpretation of the overall network process. Finally, we adopt a Bayesian inferential approach to illustrate the new methodology by …

Optimizing Electrospun Ceramic Nanofiber Strength Through Two-Step Sintering, Michael Ross

Materials Engineering

Two-step sintering (TSS) consists of a high-temperature step and immediate cooling to a sintering temperature for an extended sintering time, where grain growth is suppressed by severe densification during the high-temperature step. TSS is adopted to enhance mechanical properties of electrospun ceramic nanofibers (CNFs), a class of porous ceramics used for environmental remediation, optoelectronics, and filtration. PVP and Ga(NO₃)₃ nanofiber mesh, provided by Lawrence Livermore National Laboratory, was shaped, oxidized, and two-step sintered to form a nanocrystalline β-Ga₂O₃ CNF tube using a high-temperature step of 1,000^oC. Sintering temperatures and times varied from …

Statistical Machine Learning Methods For Mining Spatial And Temporal Data, Fei Tan

Dissertations

Spatial and temporal dependencies are ubiquitous properties of data in numerous domains. The popularity of spatial and temporal data mining has thus grown with the increasing prevalence of massive data. The presence of spatial and temporal attributes not only provides complementary useful perspectives, but also poses new challenges to the representation and integration into the learning procedure. In this dissertation, the involved spatial and temporal dependencies are explored with three genres: sample-wise, feature-wise, and target-wise. A family of novel methodologies is developed accordingly for the dependency representation in respective scenarios.

First, dependencies among discrete, continuous and repeated observations are studied …

Advances In Measurement Error Modeling, Linh Nghiem

Statistical Science Theses and Dissertations

Measurement error in observations is widely known to cause bias and a loss of power when fitting statistical models, particularly when studying distribution shape or the relationship between an outcome and a variable of interest. Most existing correction methods in the literature require strong assumptions about the distribution of the measurement error, or rely on ancillary data which is not always available. This limits the applicability of these methods in many situations. Furthermore, new correction approaches are also needed for high-dimensional settings, where the presence of measurement error in the covariates adds another level of complexity to the desirable structure …

Samples, Unite! Understanding The Effects Of Matching Errors On Estimation Of Total When Combining Data Sources, Benjamin Williams

Statistical Science Theses and Dissertations

Much recent research has focused on methods for combining a probability sample with a non-probability sample to improve estimation by making use of information from both sources. If units exist in both samples, it becomes necessary to link the information from the two samples for these units. Record linkage is a technique to link records from two lists that refer to the same unit but lack a unique identifier across both lists. Record linkage assigns a probability to each potential pair of records from the lists so that principled matching decisions can be made. Because record linkage is a probabilistic …

Measuring Clinical Weight Loss In Young Children With Severe Obesity: Comparison Of Outcomes Using Zbmi, Modified Zbmi, And Percent Of 95th Percentile, Carolyn Bates

Research Days

No abstract provided.

What Makes A Good Research Consultant?, Justin Harding, Samantha Estrada, Michael Floren

The Qualitative Report

Statistical and research consulting is defined as the collaboration of a statistician or methodologist with another professional for devising solutions to research problems. An in-depth, interview qualitative approach was taken to answer the research question of what makes a good research consultant. The authors interviewed four faculty members in the field of statistics and research methods and two experienced graduate student consultants. In-depth, face-to-face interviews revealed common themes regarding consultancy skills, resourcefulness, communication and interpersonal skills. The participants discussed how to improve consulting sessions and deal with clients with different statistics levels and backgrounds. Participants felt there was no difference …

Visualization And Machine Learning Techniques For Nasa’S Em-1 Big Data Problem, Antonio P. Garza Iii, Jose Quinonez, Misael Santana, Nibhrat Lohia

SMU Data Science Review

In this paper, we help NASA solve three Exploration Mission-1 (EM-1) challenges: data storage, computation time, and visualization of complex data. NASA is studying one year of trajectory data to determine available launch opportunities (about 90TBs of data). We improve data storage by introducing a cloud-based solution that provides elasticity and server upgrades. This migration will save $120k in infrastructure costs every four years, and potentially avoid schedule slips. Additionally, it increases computational efficiency by 125%. We further enhance computation via machine learning techniques that use the classic orbital elements to predict valid trajectories. Our machine learning model decreases trajectory …

Dynamic Sampling Versions Of Popular Spc Charts For Big Data Analysis, Samuel Anyaso-Samuel

Boise State University Theses and Dissertations

The statistical process control (SPC) chart is an effective tool for the analysis, interpretation, and visualization of data from sequential processes. Commonly used SPC charts such as the Shewhart, CUSUM and EWMA charts are widely implemented in detecting distributional shifts in various processes. With recent scientific and technological advancements, massive amounts of data continue to be generated by production, medical, agricultural and many other industrial processes. Conventional SPC charts have significant drawbacks in monitoring such processes, specifically when the velocity of the data flow is greater than the run time of the monitoring procedure. In the literature, dynamic sampling control …

Comparison Of Imputation Methods For Mixed Data Missing At Random, Kaitlyn Heidt

Electronic Theses and Dissertations

A statistician's job is to produce statistical models. When these models are precise and unbiased, we can relate them to new data appropriately. However, when data sets have missing values, assumptions to statistical methods are violated and produce biased results. The statistician's objective is to implement methods that produce unbiased and accurate results. Research in missing data is becoming popular as modern methods that produce unbiased and accurate results are emerging, such as MICE in R, a statistical software. Using real data, we compare four common imputation methods, in the MICE package in R, at different levels of missingness. The …

Vulnerability Of Industrial Facilities In The Lower Mississippi River Industrial Corridor To Relative Sea Level Rise And Tropical Cyclone Storm Surge, Joseph Blake Harris

LSU Doctoral Dissertations

Relative sea level rise (RSLR) and tropical cyclone-induced storm surge are major threats to the Lower Mississippi River Industrial Corridor (LMRIC) which has approximately 120 industrial complexes located within the corridor. Spatial interpolation methods were applied to the 2004 National Oceanic and Atmospheric published Technical Report #50 subsidence dataset and cross-validation techniques were used to determine the accuracy of each method. Digital elevation models (DEMs) were created for the years 2025, 2050, and 2075, based on these predictive surface of subsidence rates. Future DEMs were utilized to model RSLR and determine the extent of storm surge on the LMRIC by …

Unified Methods For Feature Selection In Large-Scale Genomic Studies With Censored Survival Outcomes, Lauren Spirko-Burns, Karthik Devarajan

COBRA Preprint Series

One of the major goals in large-scale genomic studies is to identify genes with a prognostic impact on time-to-event outcomes which provide insight into the disease's process. With rapid developments in high-throughput genomic technologies in the past two decades, the scientific community is able to monitor the expression levels of tens of thousands of genes and proteins resulting in enormous data sets where the number of genomic features is far greater than the number of subjects. Methods based on univariate Cox regression are often used to select genomic features related to survival outcome; however, the Cox model assumes proportional hazards …

Large Scale Dynamical Model Of Macrophage/Hiv Interactions, Sean T. Bresnahan, Matthew M. Froid

UNO Student Research and Creative Activity Fair

Properties emerge from the dynamics of large-scale molecular networks that are not discernible at the individual gene or protein level. Mathematical models - such as probabilistic Boolean networks - of molecular systems offer a deeper insight into how these emergent properties arise. Here, we introduce a non-linear, deterministic Boolean model of protein, gene, and chemical interactions in human macrophage cells during HIV infection. Our model is composed of 713 nodes with 1583 interactions between nodes and is responsive to 38 different inputs including signaling molecules, bacteria, viruses, and HIV viral particles. Additionally, the model accurately simulates the dynamics of over …

Neural Shrubs: Using Neural Networks To Improve Decision Trees, Kyle Caudle, Randy Hoover, Aaron Alphonsus

SDSU Data Science Symposium

Decision trees are a method commonly used in machine learning to either predict a categorical response or a continuous response variable. Once the tree partitions the space, the response is either determined by the majority vote – classification trees, or by averaging the response values – regression trees. This research builds a standard regression tree and then instead of averaging the responses, we train a neural network to determine the response value. We have found that our approach typically increases the predicative capability of the decision tree. We have 2 demonstrations of this approach that we wish to present as …

Session: 4 Multilinear Subspace Learning And Its Applications To Machine Learning, Randy Hoover, Kyle Caudle Dr., Karen Braman Dr.

SDSU Data Science Symposium

Multi-dimensional data analysis has seen increased interest in recent years. With more and more data arriving as 2-dimensional arrays (images) as opposed to 1-dimensioanl arrays (signals), new methods for dimensionality reduction, data analysis, and machine learning have been pursued. Most notably have been the Canonical Decompositions/Parallel Factors (commonly referred to as CP) and Tucker decompositions (commonly regarded as a high order SVD: HOSVD). In the current research we present an alternate method for computing singular value and eigenvalue decompositions on multi-way data through an algebra of circulants and illustrate their application to two well-known machine learning methods: Multi-Linear Principal Component …

A Novel Pathway-Based Distance Score Enhances Assessment Of Disease Heterogeneity In Gene Expression, Yunqing Liu, Xiting Yan

Yale Day of Data

Distance-based unsupervised clustering of gene expression data is commonly used to identify heterogeneity in biologic samples. However, high noise levels in gene expression data and the relatively high correlation between genes are often encountered, so traditional distances such as Euclidean distance may not be effective at discriminating the biological differences between samples. In this study, we developed a novel computational method to assess the biological differences based on pathways by assuming that ontologically defined biological pathways in biologically similar samples have similar behavior. Application of this distance score results in more accurate, robust, and biologically meaningful clustering results in both …

Missing Data Augmentation For Bayesian Multiplex Ergms, Robert Krause, Alberto Caimo

Conference papers

In this paper we present an estimation algorithm for Bayesian multiplex exponential random graphs (BmERGMs) under missing net- work data. Social actors are often connected with more than one type of relation, thus forming a multiplex network. It is important to consider these multiplex structures simultaneously when analyzing a multiplex network. The importance of proper models of multiplex network structures is even more pronounced under the issue of missing network data. The proposed algorithm is able to estimate BmERGMs under missing data and can be used to obtain proper multiple imputations for multiplex network structures. It is an extension of …

Exploring The Variance Of The Sample Variance Through Estimation And Simulation, Christina Stradwick

Theses, Dissertations and Capstones

In this thesis, we examine properties of the variance of the sample variance, which we will denote V (S ² ). We derive a formula for this variance and show that it only depends on the sample size, variance, and kurtosis of the underlying distribution. We also derive the maximum likelihood estimators for this parameter, V^ˆ (S ² ), under the normal, exponential, Bernoulli, and Poisson distributions and end the thesis with simulations demonstrating the distributions of these estimators.

Estimation Of Multivariate Asset Models With Jumps, Angela Loregian, Laura Ballotta, Gianluca Gianluca Fusai, Marcos Fabricio Perez

Business Faculty Publications

We propose a consistent and computationally efficient two-step methodology for the estimation of multidimensional non-Gaussian asset models built using Levy processes. The proposed framework allows for dependence between assets and different tail behaviors and jump structures for each asset. Our procedure can be applied to portfolios with a large number of assets as it is immune to estimation dimensionality problems. Simulations show good finite sample properties and significant efficiency gains. This method is especially relevant for risk management purposes such as, for example, the computation of portfolio Value at Risk and intra-horizon Value at Risk, as we show in detail …

Controlling For Confounding Via Propensity Score Methods Can Result In Biased Estimation Of The Conditional Auc: A Simulation Study, Hadiza I. Galadima, Donna K. Mcclish

Community & Environmental Health Faculty Publications

In the medical literature, there has been an increased interest in evaluating association between exposure and outcomes using nonrandomized observational studies. However, because assignments to exposure are not random in observational studies, comparisons of outcomes between exposed and nonexposed subjects must account for the effect of confounders. Propensity score methods have been widely used to control for confounding, when estimating exposure effect. Previous studies have shown that conditioning on the propensity score results in biased estimation of conditional odds ratio and hazard ratio. However, research is lacking on the performance of propensity score methods for covariate adjustment when estimating the …