Statistical Methodology Commons^™

Fast Covariance Estimation For High-Dimensional Functional Data, Luo Xiao, David Ruppert, Vadim Zipunnikov, Ciprian Crainiceanu

Johns Hopkins University, Dept. of Biostatistics Working Papers

For smoothing covariance functions, we propose two fast algorithms that scale linearly with the number of observations per function. Most available methods and software cannot smooth covariance matrices of dimension J x J with J>500; the recently introduced sandwich smoother is an exception, but it is not adapted to smooth covariance matrices of large dimensions such as J \ge 10,000. Covariance matrices of order J=10,000, and even J=100,000$ are becoming increasingly common, e.g., in 2- and 3-dimensional medical imaging and high-density wearable sensor data. We introduce two new algorithms that can handle very large covariance matrices: 1) FACE: a …

Trial Designs That Simultaneously Optimize The Population Enrolled And The Treatment Allocation Probabilities, Brandon S. Luber, Michael Rosenblum, Antoine Chambaz

Johns Hopkins University, Dept. of Biostatistics Working Papers

Standard randomized trials may have lower than desired power when the treatment effect is only strong in certain subpopulations. This may occur, for example, in populations with varying disease severities or when subpopulations carry distinct biomarkers and only those who are biomarker positive respond to treatment. To address such situations, we develop a new trial design that combines two types of preplanned rules for updating how the trial is conducted based on data accrued during the trial. The aim is a design with greater overall power and that can better determine subpopulation specific treatment effects, while maintaining strong control of …

Death Certificate Completion Skills Of Hospital Physicians In A Developing Country, Ahmed Suleman Haque, Kanza Shamim, Najm Hasan Siddiqui, Muhammad Irfan, Javaid Ahmed Khan

Section of Pulmonary & Critical Care

Background

Death certificates (DC) can provide valuable health status data regarding disease incidence, prevalence and mortality in a community. It can guide local health policy and help in setting priorities. Incomplete and inaccurate DC data, on the other hand, can significantly impair the precision of a national health information database. In this study we evaluated the accuracy of death certificates at a tertiary care teaching hospital in a Karachi, Pakistan.

Methods

A retrospective study conducted at Aga Khan University Hospital, Karachi, Pakistan for a period of six months. Medical records and death certificates of all patients who died under adult …

Ensemble-Based Methods For Forecasting Census In Hospital Units, Devin C. Koestler, Hernando Ombao, Jesse Bender

Dartmouth Scholarship

The ability to accurately forecast census counts in hospital departments has considerable implications for hospital resource allocation. In recent years several different methods have been proposed forecasting census counts, however many of these approaches do not use available patient-specific information. In this paper we present an ensemble-based methodology for forecasting the census under a framework that simultaneously incorporates both (i) arrival trends over time and (ii) patient-specific baseline and time-varying information. The proposed model for predicting census has three components, namely: current census count, number of daily arrivals and number of daily departures. To model the number of daily arrivals, …

Targeted Maximum Likelihood Estimation For Dynamic And Static Longitudinal Marginal Structural Working Models, Maya L. Petersen, Joshua Schwab, Susan Gruber, Nello Blaser, Michael Schomaker, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

This paper describes a targeted maximum likelihood estimator (TMLE) for the parameters of longitudinal static and dynamic marginal structural models. We consider a longitudinal data structure consisting of baseline covariates, time-dependent intervention nodes, intermediate time-dependent covariates, and a possibly time dependent outcome. The intervention nodes at each time point can include a binary treatment as well as a right-censoring indicator. Given a class of dynamic or static interventions, a marginal structural model is used to model the mean of the intervention specific counterfactual outcome as a function of the intervention, time point, and possibly a subset of baseline covariates. Because …

Balancing Score Adjusted Targeted Minimum Loss-Based Estimation, Samuel D. Lendle, Bruce Fireman, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

Adjusting for a balancing score is sufficient for bias reduction when estimating causal effects including the average treatment effect and effect among the treated. Estimators that adjust for the propensity score in a nonparametric way, such as matching on an estimate of the propensity score, can be consistent when the estimated propensity score is not consistent for the true propensity score but converges to some other balancing score. We call this property the balancing score property, and discuss a class of estimators that have this property. We introduce a targeted minimum loss-based estimator (TMLE) for a treatment specific mean with …

Optimal Tests Of Treatment Effects For The Overall Population And Two Subpopulations In Randomized Trials, Using Sparse Linear Programming, Michael Rosenblum, Han Liu, En-Hsu Yen

Johns Hopkins University, Dept. of Biostatistics Working Papers

We propose new, optimal methods for analyzing randomized trials, when it is suspected that treatment effects may differ in two predefined subpopulations. Such sub-populations could be defined by a biomarker or risk factor measured at baseline. The goal is to simultaneously learn which subpopulations benefit from an experimental treatment, while providing strong control of the familywise Type I error rate. We formalize this as a multiple testing problem and show it is computationally infeasible to solve using existing techniques. Our solution involves a novel approach, in which we first transform the original multiple testing problem into a large, sparse linear …

A Bayesian Regression Tree Approach To Identify The Effect Of Nanoparticles Properties On Toxicity Profiles, Cecile Low-Kam, Haiyuan Zhang, Zhaoxia Ji, Tian Xia, Jeffrey I. Zinc, Andre Nel, Donatello Telesca

COBRA Preprint Series

We introduce a Bayesian multiple regression tree model to characterize relationships between physico-chemical properties of nanoparticles and their in-vitro toxicity over multiple doses and times of exposure. Unlike conventional models that rely on data summaries, our model solves the low sample size issue and avoids arbitrary loss of information by combining all measurements from a general exposure experiment across doses, times of exposure, and replicates. The proposed technique integrates Bayesian trees for modeling threshold effects and interactions, and penalized B-splines for dose and time-response surfaces smoothing. The resulting posterior distribution is sampled via a Markov Chain Monte Carlo algorithm. This …

Analysis Of Spatial Data, Xiang Zhang

Theses and Dissertations--Statistics

In many areas of the agriculture, biological, physical and social sciences, spatial lattice data are becoming increasingly common. In addition, a large amount of lattice data shows not only visible spatial pattern but also temporal pattern (see, Zhu et al. 2005). An interesting problem is to develop a model to systematically model the relationship between the response variable and possible explanatory variable, while accounting for space and time effect simultaneously.

Spatial-temporal linear model and the corresponding likelihood-based statistical inference are important tools for the analysis of spatial-temporal lattice data. We propose a general asymptotic framework for spatial-temporal linear models and …

Income Inequality Measures And Statistical Properties Of Weighted Burr-Type And Related Distributions, Meznah R. Al Buqami

College of Graduate Studies: Theses & Dissertations

In this thesis, tail conditional expectation (TCE) in risk analysis, an important measure for right-tail risk, is presented. This value is generally based on the quantile of the loss distribution. Explicit formulas of several tail conditional expectations and inequality measures for Dagum-type models are derived. In addition, a new class of weighted Burr-III (WBIII) distribution is presented. The statistical properties of this distribution including hazard and reverse hazard functions, moments, coefficient of variation, skewness, and kurtosis, inequality measures, entropy are derived. Also, Fisher information and maximum likelihood estimates of the model parameters are obtained.

Group Testing Regression Models, Boan Zhang

Department of Statistics: Dissertations, Theses, and Student Research

Group testing, where groups of individual specimens are composited to test for the presence or absence of a disease (or some other binary characteristic), is a procedure commonly used to reduce the costs of screening a large number of individuals. Statistical research in group testing has traditionally focused on a homogeneous population, where individuals are assumed to have the same probability of having a disease. However, individuals often have different risks of positivity, so recent research has examined regression models that allow for heterogeneity among individuals within the population. This dissertation focuses on two problems involving group testing regression models. …

Quest For Continuous Improvement: Gathering Feedback And Data Through Multiple Methods To Evaluate And Improve A Library’S Discovery Tool, Jeanne M. Brown

Library Faculty Presentations

Summon at UNLV

• Implemented fall 2011: a web-scale discovery tool
• Expectations for Summon
• Continuous Summon Improvement (CSI)Group

The environment

• User changes
• Library changes
• Vendor changes
• Product changes
• Complex information environment
• Change + complexity = need to assess using multiple streams of feedback

Finding A Better Confidence Interval For A Single Regression Changepoint Using Different Bootstrap Confidence Interval Procedures, Bodhipaksha Thilakarathne

College of Graduate Studies: Theses & Dissertations

Recently a number of papers have been published in the area of regression changepoints but there is not much literature concerning confidence intervals for regression changepoints. The purpose of this paper is to find a better bootstrap confidence interval for a single regression changepoint. ("Better" confidence interval means having a minimum length and coverage probability which is close to a chosen significance level). Several methods will be used to find bootstrap confidence intervals. Among those methods a better confidence interval will be presented.

A Prior-Free Framework Of Coherent Inference And Its Derivation Of Simple Shrinkage Estimators, David R. Bickel

COBRA Preprint Series

The reasoning behind uses of confidence intervals and p-values in scientific practice may be made coherent by modeling the inferring statistician or scientist as an idealized intelligent agent. With other things equal, such an agent regards a hypothesis coinciding with a confidence interval of a higher confidence level as more certain than a hypothesis coinciding with a confidence interval of a lower confidence level. The agent uses different methods of confidence intervals conditional on what information is available. The coherence requirement means all levels of certainty of hypotheses about the parameter agree with the same distribution of certainty over parameter …

Investigation Of Trends And Predictive Effectiveness Of Crash Severity Models, James E. Mooradian

Master's Theses

This thesis describes analysis using ordinal logistic regression to uncover temporal patterns in the severity level (fatal, serious injury, minor injury, slight injury or no injury) for persons involved in highway crashes in Connecticut, focusing on the demographic split between senior travelers (65 years and over) and non-senior travelers. Existing state sources provide data describing the time and weather conditions for each crash and the vehicles and persons involved over the time period from 1995 to 2009 as well as the traffic volumes and the characteristics of the roads on which these crashes occurred. Findings indicate an overall increase in …

Confidence Intervals For The Selected Population In Randomized Trials That Adapt The Population Enrolled, Michael Rosenblum

Johns Hopkins University, Dept. of Biostatistics Working Papers

It is a challenge to design randomized trials when it is suspected that a treatment may benefit only certain subsets of the target population. In such situations, trial designs have been proposed that modify the population enrolled based on an interim analysis, in a preplanned manner. For example, if there is early evidence that the treatment only benefits a certain subset of the population, enrollment may then be restricted to this subset. At the end of such a trial, it is desirable to draw inferences about the selected population. We focus on constructing confidence intervals for the average treatment effect …

Using The R Library Rpanel For Gui-Based Simulations In Introductory Statistics Courses, Ryan M. Allison

Statistics

As a student, I noticed that the statistical package R (http://www.r-project.org) would have several benefits of its usage in the classroom. One benefit to the package is its free and open-source nature. This would be a great benefit for instructors and students alike since it would be of no cost to use, unlike other statistical packages. Due to this, students could continue using the program after their statistical courses and into their professional careers. It would be good to expose students while they are in school to a tool that professionals use in industry. R also has powerful …

Differential Patterns Of Interaction And Gaussian Graphical Models, Masanao Yajima, Donatello Telesca, Yuan Ji, Peter Muller

COBRA Preprint Series

We propose a methodological framework to assess heterogeneous patterns of association amongst components of a random vector expressed as a Gaussian directed acyclic graph. The proposed framework is likely to be useful when primary interest focuses on potential contrasts characterizing the association structure between known subgroups of a given sample. We provide inferential frameworks as well as an efficient computational algorithm to fit such a model and illustrate its validity through a simulation. We apply the model to Reverse Phase Protein Array data on Acute Myeloid Leukemia patients to show the contrast of association structure between refractory patients and relapsed …

Avoiding Boundary Estimates In Linear Mixed Models Through Weakly Informative Priors, Yeojin Chung, Sophia Rabe-Hesketh, Andrew Gelman, Jingchen Liu, Vincent Dorie

U.C. Berkeley Division of Biostatistics Working Paper Series

Variance parameters in mixed or multilevel models can be difficult to estimate, especially when the number of groups is small. We propose a maximum penalized likelihood approach which is equivalent to estimating variance parameters by their marginal posterior mode, given a weakly informative prior distribution. By choosing the prior from the gamma family with at least 1 degree of freedom, we ensure that the prior density is zero at the boundary and thus the marginal posterior mode of the group-level variance will be positive. The use of a weakly informative prior allows us to stabilize our estimates while remaining faithful …

The Quotient Of The Beta-Weibull Distribution, Nonhle Channon Mdziniso

Theses, Dissertations and Capstones

A new class of distributions recently developed involves the logit of the beta distribution. Among this class of distributions are, the beta-Normal (Eugene et al. [15]); beta-Gumbel (Nadarajah and Kotz [18]); beta-Exponential (Nadarajah and Kotz [19]); beta-Weibull (Famoye et al. [6]); beta-Rayleigh (Akinsete and Lowe [3]); beta-Laplace (Kozubowshi and Nadarajah [20]); and beta-Pareto (Akinsete et al. [4]), among a few others. Many useful statistical properties arising from these distributions and their applications to real life data have been discussed in literature. One approach by which a new statistical distribution is generated is by the transformation of random variables having known …