Statistics and Probability Commons^™

Validated Automatic Brain Extraction Of Head Ct Images, John Muschelli Iii, Natalie L. Ullman, Daniel F. Hanley, Paul Vespa, Ciprian M. Crainiceanu

John Muschelli III

Background

X-ray Computed Tomography (CT) imaging of the brain is commonly used in diagnostic settings. Al- though CT scans are primarily used in clinical practice, they are increasingly used in research. A fundamental processing step in brain imaging research is brain extraction – the process of separating the brain tissue from all other tissues. Methods for brain extraction have either been validated but not fully automated, or have been fully automated and informally proposed, but never formally validated.

Aim

To systematically analyze and validate the performance of FSL’s brain extraction tool (BET) on head CT images of patients with intracranial ...

Session B-2: The “Roll” Of Statistics In Modeling - It All Adds Up, Richard Stalmack, Janice Krouse

Professional Learning Day

The common core practice standards ask us to teach students to propose mathematical models and test their viability. Participants will do an experiment, collect data and use technological tools to combine modeling, analysis and basic statistics. Participants should bring a laptop, if possible; otherwise, bring a graphing calculator.

Leveraging Prognostic Baseline Variables To Gain Precision In Randomized Trials, Elizabeth Colantuoni, Michael Rosenblum

Johns Hopkins University, Dept. of Biostatistics Working Papers

We focus on estimating the average treatment effect in a randomized trial. If baseline variables are correlated with the outcome, then appropriately adjusting for these variables can improve precision. An example is the analysis of covariance (ANCOVA) estimator, which applies when the outcome is continuous, the quantity of interest is the difference in mean outcomes comparing treatment versus control, and a linear model with only main effects is used. ANCOVA is guaranteed to be at least as precise as the standard unadjusted estimator, asymptotically, under no parametric model assumptions, and also is locally, semiparametric efficient. Recently, several estimators have been ...

Simulation Of Semicompeting Risk Survival Data And Estimation Based On Multistate Frailty Model, Fei Jiang, Sebastien Haneuse

Harvard University Biostatistics Working Paper Series

We develop a simulation procedure to simulate the semicompeting risk survival data. In addition, we introduce an EM algorithm and a B–spline based estimation procedure to evaluate and implement Xu et al. (2010)’s nonparametric likelihood es- timation approach. The simulation procedure provides a route to simulate samples from the likelihood introduced in Xu et al. (2010)’s. Further, the EM algorithm and the B–spline methods stabilize the estimation and gives accurate estimation results. We illustrate the simulation and the estimation procedure with simluation examples and real data analysis.

Optimal Dynamic Treatments In Resource-Limited Settings, Alexander R. Luedtke, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

A dynamic treatment rule (DTR) is a treatment rule which assigns treatments to individuals based on (a subset of) their measured covariates. An optimal DTR is the DTR which maximizes the population mean outcome. Previous works in this area have assumed that treatment is an unlimited resource so that the entire population can be treated if this strategy maximizes the population mean outcome. We consider optimal DTRs in settings where the treatment resource is limited so that there is a maximum proportion of the population which can be treated. We give a general closed-form expression for an optimal stochastic DTR ...

The Game Of Thrones: A Study Of Power Networks And How They Change, Trevor Williams

Research on Capitol Hill

No abstract provided.

Negative Binomial Regerssion, 2nd Ed, 2nd Print, Errata And Comments, Joseph Hilbe

Joseph M Hilbe

Errata and Comments for 2nd printing of NBR2, 2nd edition. Previous errata from first printing all corrected. Some added and new text as well.

Modeling Count Data; Errata And Comments, Joseph M. Hilbe

Joseph M Hilbe

Modeling Count Data: Errata and Comments PDF. Will be updated on a continuing basis.

Applying Multiple Imputation For External Calibration To Propensty Score Analysis, Yenny Webb-Vargas, Kara E. Rudolph, D. Lenis, Peter Murakami, Elizabeth A. Stuart

Johns Hopkins University, Dept. of Biostatistics Working Papers

Although covariate measurement error is likely the norm rather than the exception, methods for handling covariate measurement error in propensity score methods have not been widely investigated. We consider a multiple imputation-based approach that uses an external calibration sample with information on the true and mismeasured covariates, Multiple Imputation for External Calibration (MI-EC), to correct for the measurement error, and investigate its performance using simulation studies. As expected, using the covariate measured with error leads to bias in the treatment effect estimate. In contrast, the MI-EC method can eliminate almost all the bias. We confirm that the outcome must be ...

Adaptive, Group Sequential Designs That Balance The Benefits And Risks Of Wider Inclusion Criteria, Michael Rosenblum, Brandon S. Luber, Richard E. Thompson, Daniel F. Hanley

Johns Hopkins University, Dept. of Biostatistics Working Papers

We propose a new class of adaptive randomized trial designs aimed at gaining the advantages of wider generalizability and faster recruitment, while mitigating the risks of including a population for which there is greater a priori uncertainty. Our designs use adaptive enrichment, i.e., they have preplanned decision rules for modifying enrollment criteria based on data accrued at interim analyses. For example, enrollment can be restricted if the participants from predefined subpopulations are not benefiting from the new treatment. To the best of our knowledge, our designs are the first adaptive enrichment designs to have all of the following features ...

Review Of Naked Statistics: Stripping The Dread From Data By Charles Wheelan, Michael T. Catalano

Numeracy

Wheelan, Charles. Naked Statistics: Stripping the Dread from Data (New York, NY, W. W. Norton & Company, 2014). 282 pp. ISBN 978-0-393-07195-5

In his review of What Numbers Say and The Numbers Game, Rob Root (Numeracy 3(1): 9) writes “Popular books on quantitative literacy need to be easy to read, reasonably comprehensive in scope, and include examples that are thought-provoking and memorable.” Wheelan’s book certainly meets this description, and should be of interest to both the general public and those with a professional interest in numeracy. A moderately diligent learner can get a decent understanding of basic statistics from ...

Functional Regression, Jeffrey S. Morris

Jeffrey S. Morris

Functional data analysis (FDA) involves the analysis of data whose ideal units of observation are functions defined on some continuous domain, and the observed data consist of a sample of functions taken from some population, sampled on a discrete grid. Ramsay and Silverman's 1997 textbook sparked the development of this field, which has accelerated in the past 10 years to become one of the fastest growing areas of statistics, fueled by the growing number of applications yielding this type of data. One unique characteristic of FDA is the need to combine information both across and within functions, which Ramsay ...

Quantile Rank Maps: A New Tool For Understanding Individual Brain Development, Huaihou Chen, Clare Kelly, F. Xavier Castellanos, Ye He, Xi-Nian Zuo, Philip T. Reiss

Philip T. Reiss

We propose a novel method for neurodevelopmental brain mapping that displays how an individual’s values for a quantity of interest compare with age-specific norms. By estimating smoothly age-varying distributions at a set of brain regions of interest, we derive age-dependent region-wise quantile ranks for a given individual, which can be presented in the form of a brain map. Such quantile rank maps could potentially be used for clinical screening. Bootstrap-based confidence intervals are proposed for the quantile rank estimates. We also propose a recalibrated Kolmogorov-Smirnov test for detecting group differences in the age-varying distribution. This test is shown to ...

Facets: Fraction And Allele-Specific Copy Number Estimates From Tumor Sequencing, Ronglai Shen, Venkatraman Seshan

Memorial Sloan-Kettering Cancer Center, Dept. of Epidemiology & Biostatistics Working Paper Series

Intratumor heterogeneity is characterized by the presence of genetically and phenotypically distinct subclones of tumor cells. Such genetic diversity within a tumor is increasingly recognized as a driver of rapid disease progression, resistance to targeted therapies, and poor survival outcome. It also has important implications in defining "actionable" driver genes in the cancer genome. To facilitate intratumor heterogeneity analysis, we developed a unified analysis pipeline called FACETS for DNA sequencing of tumor-normal pairs (including whole-exome, whole-genome, and targeted capture sequencing), to 1) perform joint segmentation of total and allelic copy ratio, and to 2) estimate tumor purity, ploidy, allele-specific copy ...

Association Between Respiratory Syncytial Virus Activity And Pneumococcal Disease In Infants: A Time Series Analysis Of Us Hospitalization Data., Daniel M. Weinberger, Keith P. Klugman, Claudia A. Steiner, Lone Simonsen, Cécile Viboud

Epidemiology and Biostatistics Faculty Publications

BACKGROUND:

The importance of bacterial infections following respiratory syncytial virus (RSV) remains unclear. We evaluated whether variations in RSV epidemic timing and magnitude are associated with variations in pneumococcal disease epidemics and whether changes in pneumococcal disease following the introduction of seven-valent pneumococcal conjugate vaccine (PCV7) were associated with changes in the rate of hospitalizations coded as RSV.

METHODS AND FINDINGS:

We used data from the State Inpatient Databases (Agency for Healthcare Research and Quality), including >700,000 RSV hospitalizations and >16,000 pneumococcal pneumonia hospitalizations in 36 states (1992/1993-2008/2009). Harmonic regression was used to estimate the timing ...

Clinical Significance Of Left Atrial Anatomic Abnormalities Identified By Cardiac Computed Tomography, Ara V. Vehian, Brian G. Choi, Satinder Rekhi, Heather A. Young, Raman S. Dusaj, Robert K. Zeman

Epidemiology and Biostatistics Faculty Publications

Purpose: The clinical significance of newly identified left atrial anatomic abnormalities (LAAA)— accessory appendages, diverticula, septal pouches—by multidetector CT (MDCT) remains unclear. Similar anatomical outpouchings, i.e., the left atrial appendage, have been associated with cardioembolisms and arrhythmia. To test the hypothesis that LAAA are also associated with increased risk of these events, we performed a retrospective analysis to examine the association of LAAA in patients undergoing CT with embolic events and arrhythmia.

Methods: 242 patients (mean age 56 SD 12 years, 41% female) were selected who had CT coronary angiography performed with 64-row MDCT between 2007 and 2012 ...

The Support Vector Machine And Mixed Integer Linear Programming: Ramp Loss Svm With L1-Norm Regularization, Eric J. Hess, J. Paul Brooks

Statistical Sciences and Operations Research Publications

The support vector machine (SVM) is a flexible classification method that accommodates a kernel trick to learn nonlinear decision rules. The traditional formulation as an optimization problem is a quadratic program. In efforts to reduce computational complexity, some have proposed using an L1-norm regularization to create a linear program (LP). In other efforts aimed at increasing the robustness to outliers, investigators have proposed using the ramp loss which results in what may be expressed as a quadratic integer programming problem (QIP). In this paper, we consider combining these ideas for ramp loss SVM with L1-norm regularization. The result is four ...

Principal Component Analysis And Optimization: A Tutorial, Robert Reris, J. Paul Brooks

Statistical Sciences and Operations Research Publications

No abstract provided.

Case Studies In Evaluating Time Series Prediction Models Using The Relative Mean Absolute Error, Nicholas G. Reich, Justin Lessler, Krzysztof Sakrejda, Stephen A. Lauer, Sopon Iamsirithaworn, Derek A T Cummings

Nicholas G Reich

Statistical prediction models inform decision-making processes in many real-world settings. Prior to using predictions in practice, one must rigorously test and validate candidate models to ensure that the proposed predictions have sufficient accuracy to be used in practice. In this paper, we present a framework for evaluating time series predictions that emphasizes computational simplicity and an intuitive interpretation using the relative mean absolute error metric. For a single time series, this metric enables comparisons of candidate model predictions against naive reference models, a method that can provide useful and standardized performance benchmarks. Additionally, in applications with multiple time series, this ...

Parity And Diabetes Risk Among Hispanic Women From Colombia: Cross-Sectional Evidence, Pablo Cure, Heather J. Hoffman, Carlos Cure-Cure

Epidemiology and Biostatistics Faculty Publications

Objective

The association between parity and type 2 diabetes has been studied in developed countries and in Singapore and Chinese women but not in Hispanics. Herein we evaluated the association between parity (number of live births) with diabetes in a group of Hispanic postmenopausal women from Colombia.

Research design and methods

Herein we evaluated the association between parity and diabetes in a population of 1,795 women from Colombia. Women were divided in birth categories (0 [referent], 1 or 2, 3–5, 6 or > births). Medical history of diabetes and anthropometric characteristics were recorded. Logistic regressions were performed in order ...