carvalho2 Carlos Carvalho

Associate Professor
Department of Statistics and Data Sciences (SDS)
Department of Information, Risk, and Operations Management (IROM)
Curriculum Vitae

I am a statistician and my research centers on the development of methodological aspects of structured probability models for large-scale multivariate problems, with applications ranging from financial time series to high-throughput cancer genomics. My work also pays special attention to the development and improvement of associated computational tools for model selection and inference. My current projects are in financial econometrics and empirical asset pricing problems.

I am from Brazil where I did my undergraduate studies. I received a Ph.D. in Statistics from Duke University in 2006. Before moving to The University of Texas, I was at The University of Chicago Booth School of Business. 

 

Paul Damidamienen

Professor
Department of Information, Risk, and Operations Management
Department of Finance
Curriculum Vitae

I am interested in Bayesian Methods and Stochastic Optimization.


 

 

DanielsMichael Daniels

Professor
Department of Statistics and Data Sciences (SDS)
Department of Integrative Bio
Curriculum Vitae

The focus of my research program revolves around incomplete longitudinal data with special attention to estimation of the dependence structures and more recently, methods for causal inference with applications to mediation. My current collaborations include clinical trials in weight management and muscular dystrophy and questions involving the impact of recent Medicare legislation on "preventable" hospital outcomes. 

I was most recently Professor and Chair in the Department of Statistics at the University of Florida.  Before that, I spent five years on the faculty at Iowa State University and two years at Carnegie Mellon University.  I received my doctoral training in biostatistics at Harvard University in the early 1990's. I am a fellow of the American Statistical Association and co-author of a well received research monograph on Bayesian methods for missing data in longitudinal studies.

 

meyersLauren Ancel Meyers

Director, Department of Statistics and Data Sciences (SDS)
Professor, Department of Integrative Biology (IB)
Curriculum Vitae

Lauren Ancel Meyers received her B.A. degree in Mathematics and Philosophy from Harvard University in 1996 and her Ph.D. from the department of Biological Sciences at Stanford University in 2000. She joined the faculty at the University of Texas at Austin in 2003 where she was recently promoted to Full Professor and awarded a Donald D. Harrington Faculty Fellowship. She has also been an active member of the external faculty of the Santa Fe Institute since 2003 and now serves on its Scientific Advisory Board. Lauren has developed new mathematical methods for forecasting and optimizing the control of infectious diseases including meningitis, HIV, influenza, walking pneumonia, and SARS. Her research has been published in over 45 peer-reviewed publications and funded by research grants from National Institutes of Health, the National Science Foundation, and the James S. McDonnell Foundation. The Wall Street Journal, Newsweek, the BBC, and other news sources have highlighted Lauren's work; and a number of government agencies have sought her expertise, including the Centers for Disease Control and Prevention (CDC), the Biomedical Advanced Research and Development Authority (BARDA), and the US National Intelligence Council. In 2004, the MIT Technology Review named Lauren as one of the top 100 global innovators under age 35.

 

MuellerPeter Müller

Professor
Department of Statistics and Data Sciences (SDS)
Department of Mathematics
Curriculum Vitae 

I am interested in methods and applications of Bayesian inference. More specifically, I am working on nonparametric Bayesian inference, decision problems, and applications to biomedical research problems. Nonparametric Bayesian inference refers to prior models for infinite dimensional random quantities, typically random probability measures. Decision problems include particular clinical trial design and multiple comparison procedures. Other applications that I am interested in include inference related to dependence structure, specifically graphical models to formalize inference about dependence for high throughput genomic data. Another large area of application is population pharmacokinetic and pharmacodynamic models, which give rise to many good applications that exploit many of my methodological interests.

My undergraduate education is from Universität Wien and Technische Universität Wien, Austria. My Ph.D. is from Purdue University where I worked under Jim Berger on MCMC for constrained parameter problems. I spent several years at the Institute of Statistics and Dec Sciences (ISDS), Duke University, and at M.D. Anderson Biostatistics.

 

pillowJonathan Pillow

Assistant Professor
Department of Psychology
Department of Neuroscience
Curriculum Vitae

My research focuses on statistical methods for neural data and the neural mechanisms underlying statistical inference in the brain. I develop Bayesian methods for high-dimensional neural datasets, with an emphasis on point process regression, dimensionality reduction, feature selection, state space models, active learning, information theory, and nonparametric models. Current problems of interest include the "neural code" for decision-making in parietal cortex, multi-neuron spike train codes, and models of intracellular responses in single neurons. My lab also conducts simple experiments investigating the optimality of statistical inference by human observers in perceptual tasks.

I received my Ph.D. in neuroscience from NYU in 2005, advised by Eero Simoncelli. From 2005–2008, I was a postdoctoral fellow at the Gatsby Computational Neuroscience Unit at University College London (UCL), working with Peter Dayan and Peter Latham. In 2009, I joined the psychology department at UT Austin, with courtesy affiliations in Neurobiology, Neuroscience and CSEM. I completed my undergraduate education at the University of Arizona, where I majored in mathematics and philosophy. I was a Fulbright Fellow in Morocco in 1997–98 studying north African literature.

 

RavikumarPradeep Ravikumar

Assistant Professor
Department of Statistics and Data Sciences (SDS)
Department of Computer Science (CS)
Curriculum Vitae 

My main area of research is in statistical machine learning. The core problem here combines the statistical imperative of inferring reliable conclusions from limited observations or data with the computational imperative of doing so with limited computation. Of particular interest are modern settings where the dimensionality of data is high, and simultaneously achieving these twin objectives is difficult. My recent research has been on the foundations of such statistical machine learning, with particular emphasis on graphical models, high-dimensional statistical inference, and optimization.

I received my BTech in Computer Science and Engineering from the Indian Institute of Technology, Bombay in India. I then received my PhD in Machine Learning from the School of Computer Science at Carnegie Mellon University, where I worked with John Lafferty. I was a postdoctoral scholar at the Department of Statistics, University of California, Berkeley from 2007–2009, where I worked with Martin Wainwright and Bin Yu. 

 

sagerTom Sager

Professor
Department of Information, Risk, and Operations Management (IROM)
Curriculum Vitae

The major part of my research focuses on the development and application of econometric models to study the empirical behavior of insurance companies. The models involve simultaneously interacting manifest and latent variables interacting in autocorrelated nonlinear panel data structures. I have applied these to the prediction of insurer insolvency, the risks of mortgage-backed securities, the effects of the Affordable Care Act, the assessment of global systemic risk, consequences of regulation, and other issues. I seek to illuminate how agency theory, transactions cost economics, theories of limited and unlimited risk, and other ideas play out to explain insurers’ management of their enterprise risks.

 

scottJames G. Scott

Assistant Professor
Department of Statistics and Data Sciences (SDS)
Department of Information, Risk, and Operations Management (IROM)
Curriculum Vitae

I am a Bayesian statistician. I study problems in model selection and multiple testing; connections between machine learning and Bayesian shrinkage estimation; variable selection and high-dimensional inference in non-linear, non-Gaussian models; and structured models for covariance matrices. Lately I've been thinking about how to make Bayesian-inspired approaches for sparse-signal detection scalable to enormous data sets, where many traditional Bayesian tools simply won't work. Some of my recent collaborations outside statistics include applied work in linguistics, neuroscience, clinical bio-informatics, and political science.

My Ph.D. is from Duke University, where I studied Bayesian model selection under Jim Berger. Before that I studied at Trinity College, Cambridge for two years. I was an undergraduate from 2000 to 2004 here at UT-Austin in the Dean's Scholars and Plan II honors programs.

 

shivelyTom Shively

Professor
Department of Information, Risk, and Operations Management (IROM)
Curriculum Vitae

My research focuses on nonparametric function estimation and its application in energy economics, finance, marketing and transportation science. Current problems of interest include estimating univariate functions nonparametrically subject to shape constraints such as monotonicity and convexity, developing tests for monotonicity, and extending these results to multivariate functions using Bayesian additive regression trees. I am also interested in MCMC-based computational methods that allow for nonparametric function estimation in a wide range of non-Gaussian models including generalized mixed models, hazard function models and models for extreme values. My recent applied research focuses on modeling electricity prices in the deregulated Australian market using multivariate nonparametric methods.

I received a B.A. degree in Mathematics from Middlebury College in 1981, an M.B.A. from the University of Chicago in 1984, and a Ph.D. in Statistics from Chicago in 1986. I have been at The University of Texas at Austin since 1986.

 

walkerStephen Walker

Professor
Department of Statistics and Data Sciences (SDS)
Department of Mathematics
Curriculum Vitae

The main focus of my research is on Bayesian parametric and nonparametric methods. I have worked on applications, methodology,  theory, implementation via MCMC, and foundational issues. My main areas of applications include medical statistics and financial data.Recent work on Bayesian nonparametrics includes constructing time series and regression models.Recent work also includes working with Bayesian models under misspecification and using loss functions as an alternative to probability models within a learning process akin to Bayesian updating.

I received my BA (Hons.) in Mathematics at the Oriel College of Oxford University, being awarded Open Exhibition on entry to the college. I received my Ph.D. in statistics from the Imperial College of London in 1995, supervised by Jon Wakefield. The focus of my research was on Bayesian parametric and nonparametric methods with applications in medical statistics. From there, I taught at various institutions: Imperial College at London, the University of Bath, and most recently at the University of Kent.

 

williamsonSinead Williamson

Assistant Professor
Department of Statistics and Data Sciences (SDS)
Department of Information, Risk, and Operations Management (IROM)
Curriculum Vitae

My main research focus is the development of nonparametric Bayesian methods for machine learning applications. In particular, I am interested in constructing distributions over correlated measures and structures, in order to model correlated data sets or data with spatio-temporal dependence. Examples include models for documents whose topical composition varies through time, and models for temporally evolving social networks. A key research goal is the development of efficient inference algorithms for such models, and I am currently investigating methods that allow us to apply Bayesian nonparametric techniques to large datasets.

 

zhouMingyuan Zhou

Assistant Professor
Department of Information, Risk, and Operations Management (IROM)
Curriculum Vitae

My research lies at the intersection of Bayesian statistics and machine learning. I am interested in developing statistical theory and methods, hierarchical models, and efficient Bayesian inference for big data. I am currently focused on the development of nonparametric Bayesian priors for both count & mixture modeling and dictionary learning. I am building the negative binomial process family to introduce new exchangeable random partitions and novel clustering algorithms.

I received my Ph.D. in Electrical and Computer Engineering from Duke University in 2013, Master's in Signal and Information Processing from the Chinese Academy of Sciences in 2008, and B.Sc. in Acoustics from Nanjing University in 2005.