My research is centered around Statistical methods for new technologies used in public health and medical studies. These technologies provide new types of data that are increasing both in size and complexity. I am interested in developing analytic tools that are tailored to specific applications, address the particular subtleties of the problem, and then find the common thread that eventually becomes Statistical methodology. My current scientific research interest centers around sleep research (EEG, polysomnograms), wearable computing (accelerometers, heart monitors), and multimodality brain imaging (SPECT, MRI, CT) with applications to Alzheimer, Multiple Sclerosis, traumatic brain injury, and cancer. My statistical expertise centers around inferential methods for ultra high dimensional data, mixed effects modeling, Bayesian inference, and smoothing.
Categorical Data Analysis
A unified approach to modeling multivariate binary data using copulas over partitions (with Bruce J. Swihart and Brian Caffo), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
Many seemingly disparate approaches for marginal modeling have been developed in recent years. We demonstrate...
Microarrays
Fast Wavelet Based Functional Models for Transcriptome Analysis with Tiling Arrays (with Lieven Clement, Kristof De Beuf, Olivier Thas, Marnik Vuylsteke, and Rafael A. Irizarry), Statistical Applications in Genetics and Molecular Biology (2012)
For a better understanding of the biology of an organism, a complete description is needed...
Epidemiology
MODEL SELECTION AND HEALTH EFFECT ESTIMATION IN ENVIRONMENTAL EPIDEMIOLOGY (with Francesca Dominici, Chi Wang, and Giovanni Parmigiani), Johns Hopkins University, Dept. of Biostatistics Working Papers (2008)
In air pollution epidemiology, improvements in statistical analysis tools can translate into significant scientific advances,...
Medical Specialties
POPULATION-WIDE MODEL-FREE QUANTIFICATION OF BLOOD-BRAIN-BARRIER DYNAMICS IN MULTIPLE SCLEROSIS (with Russell T. Shinohara, Brian Caffo, María Inés Gaitán, and Daniel Reich), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
The processes by which new white matter lesions in multiple sclerosis (MS) develop are only...
NONLINEAR TUBE-FITTING FOR THE ANALYSIS OF ANATOMICAL AND FUNCTIONAL STRUCTURES (with Jeff Goldsmith, Brian S. Caffo, Daniel Reich, Yong Du, and Craig Hendrix), Johns Hopkins University, Dept. of Biostatistics Working Papers (2009)
We are concerned with the estimation of the exterior surface of tube-shaped anatomical structures. This...
Disease Modeling
BIVARIATE BINOMIAL SPATIAL MODELLING LOA loa PREVALENCE IN TROPICAL AFRICA (with Peter J. Diggle and Barry Rowlingson), Johns Hopkins University, Dept. of Biostatistics Working Papers (2006)
We present a state-of-the-art application of smoothing for dependent bivariate binomial spatial data to Loa...
Multivariate Analysis
LIKELIHOOD BASED POPULATION INDEPENDENT COMPONENT ANALYSIS (with Ani Eloyan and Brian S. Caffo), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
Independent component analysis (ICA) is a widely used technique for blind source separation, used heavily...
A unified approach to modeling multivariate binary data using copulas over partitions (with Bruce J. Swihart and Brian Caffo), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
Many seemingly disparate approaches for marginal modeling have been developed in recent years. We demonstrate...
Spatially Adaptive Bayesian P-Splines with Heteroscedastic Errors (with David Ruppert and Raymond J. Carroll), Johns Hopkins University, Dept. of Biostatistics Working Papers (2004)
An increasingly popular tool for nonparametric smoothing are penalized splines (P-splines) which use low-rank spline...
Computation
Bayesian Analysis for Penalized Spline Regression Using Win BUGS (with David Ruppert and M.P. Wand), Johns Hopkins University, Dept. of Biostatistics Working Papers (2007)
Penalized splines can be viewed as BLUPs in a mixed model framework, which allows the...
Semiparametric Regression in Capture-Recapture Modelling (with O. Gimenez, C. Barbraud, S. Jenouvrier, and B.T. Morgan), Johns Hopkins University, Dept. of Biostatistics Working Papers (2004)
Capture-recapture models were developed to estimate survival using data arising from marking and monitoring wild...
Spatially Adaptive Bayesian P-Splines with Heteroscedastic Errors (with David Ruppert and Raymond J. Carroll), Johns Hopkins University, Dept. of Biostatistics Working Papers (2004)
An increasingly popular tool for nonparametric smoothing are penalized splines (P-splines) which use low-rank spline...
Longitudinal Data Analysis and Time Series
A unified approach to modeling multivariate binary data using copulas over partitions (with Bruce J. Swihart and Brian Caffo), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
Many seemingly disparate approaches for marginal modeling have been developed in recent years. We demonstrate...
Modeling multilevel sleep transitional data via Poisson log-linear multilevel models (with Bruce J. Swihart, Brian Caffo, and Naresh M. Punjabi), Johns Hopkins University, Dept. of Biostatistics Working Papers (2009)
This paper proposes Poisson log-linear multilevel models to investigate population variability in sleep state transition...
General Biostatistics
LONGITUDINAL ANALYSIS OF SPATIOTEMPORAL PROCESSES: A CASE STUDY OF DYNAMIC CONTRAST-ENHANCED MAGNETIC RESONANCE IMAGING IN MULTIPLE SCLEROSIS (with Russell T. Shinohara, Brian S. Caffo, and Daniel S. Reich), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
Multiple sclerosis (MS) is an immune-mediated disease in which inflammatory lesions form in the brain....
MOVELETS: A DICTIONARY OF MOVEMENT (with Jiawei Bai, Jeff Goldsmith, Brian Caffo, and Thomas A. Glass), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
Recent technological advances provide researchers a way of gathering real-time information on an individual’s movement...
STATISTICAL INFERENCE ON THE DIFFERENCE IN THE MEANS OF TWO CORRELATED FUNCTIONAL PROCESSES: AN APPLICATION TO SLEEP EEG POWER SPECTRA (with Ana-Maria Staicu, Shubankar Ray, and Naresh Punjabi), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
Nonparametric inference methods on the mean difference between two correlated functional processes are proposed. We...
MODELING FUNCTIONAL DATA WITH SPATIALLY HETEROGENEOUS SHAPE CHARACTERISTICS (with Ana-Maria Staicu, Daniel S. Reich, and David Ruppert), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
We propose a novel class of models for functional data exhibiting skewness or other shape...
POPULATION VALUE DECOMPOSITION, A FRAMEWORK FOR THE ANALYSIS OF IMAGE POPULATIONS (with Brian S. Caffo, Sheng Luo, and Vadim Zipunnikov), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
Images, often stored in multidimensional arrays are fast becoming ubiquitous in medical and public health...
Statistical Models
Mixed effect Poisson log-linear models for clinical and epidemiological sleep hypnogram data (with Bruce J. Swihart; Brian S. Caffo PhD; and Naresh M. Punjabi PhD, MD), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
Bayesian Poisson log-linear multilevel models scalable to epidemiological studies are proposed to investigate population variability...
A unified approach to modeling multivariate binary data using copulas over partitions (with Bruce J. Swihart and Brian Caffo), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
Many seemingly disparate approaches for marginal modeling have been developed in recent years. We demonstrate...
Multilevel Functional Principal Component Analysis (with Chong-Zhi Di, Brian S. Caffo, and Naresh M. Punjabi), Annals of Applied Statistics (2009)
The Sleep Heart Health Study (SHHS) is a comprehensive landmark study of sleep and its...
Bayesian Analysis for Penalized Spline Regression Using Win BUGS (with David Ruppert and M.P. Wand), Johns Hopkins University, Dept. of Biostatistics Working Papers (2007)
Penalized splines can be viewed as BLUPs in a mixed model framework, which allows the...
COX MODELS WITH NONLINEAR EFFECT OF COVARIATES MEASURED WITH ERROR: A CASE STUDY OF CHRONIC KIDNEY DISEASE INCIDENCE (with David Ruppert and Josef Coresh), Johns Hopkins University, Dept. of Biostatistics Working Papers (2006)
We propose, develop and implement the simulation extrapolation (SIMEX) methodology for Cox regression models when...
Statistical Theory and Methods
LONGITUDINAL HIGH-DIMENSIONAL DATA ANALYSIS (with Vadim Zipunnikov, Sonja Greven, Brian Caffo, and Daniel S. Reich), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
We develop a flexible framework for modeling high-dimensional functional and imaging data observed longitudinally. The...
CORRECTED CONFIDENCE BANDS FOR FUNCTIONAL DATA USING PRINCIPAL COMPONENTS (with Jeff Goldsmith and Sonja Greven), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
Functional principal components (FPC) analysis is widely used to decompose and express functional observations. Curve...
FUNCTIONAL PRINCIPAL COMPONENTS MODEL FOR HIGH-DIMENSIONAL BRAIN IMAGING (with Vadim Zipunnikov, Brian S. Caffo, David M. Yousem, Christos Davatzikos, and Brian S. Schwartz), Johns Hopkins University, Dept. of Biostatistics Working Papers (2011)
We establish a fundamental equivalence between singular value decomposition (SVD) and functional principal components analysis...
MULTILEVEL FUNCTIONAL PRINCIPAL COMPONENT ANALYSIS FOR HIGH-DIMENSIONAL DATA (with Vadim Zipunnikov, Brian Caffo, David M. Yousem, Christos Davatzikos, and Brian S. Schwartz), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
We propose fast and scalable statistical methods for the analysis of hundreds or thousands of...
LONGITUDINAL PENALIZED FUNCTIONAL REGRESSION (with Jeff Goldsmith, Brian Caffo, and Daniel Reich), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
We propose a new regression model and inferential tools for the case when both the...
Computational Biology/Bioinformatics
Fast Wavelet Based Functional Models for Transcriptome Analysis with Tiling Arrays (with Lieven Clement, Kristof De Beuf, Olivier Thas, Marnik Vuylsteke, and Rafael A. Irizarry), Statistical Applications in Genetics and Molecular Biology (2012)
For a better understanding of the biology of an organism, a complete description is needed...
WAVELET BASED FUNCTIONAL MODELS FOR TRANSCRIPTOME ANALYSIS WITH TILING ARRAYS (with Lieven Clement, Kristof DeBeuf, Olivier Thas, Marnik Vuylsteke, and Rafael Irizarry), Johns Hopkins University, Dept. of Biostatistics Working Papers (2010)
For a better understanding of the biology of an organism a complete description is needed...