Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



David B. Dunson, Arts and Sciences Distinguished Professor of Statistical Science and Arts and Sciences Professor of Mathematics and Faculty Network Member of Duke Institute for Brain Sciences

David B. Dunson

My research focuses on developing new tools for probabilistic learning from complex data - methods development is directly motivated by challenging applications in ecology/biodiversity, neuroscience, environmental health, criminal justice/fairness, and more.  We seek to develop new modeling frameworks, algorithms and corresponding code that can be used routinely by scientists and decision makers.  We are also interested in new inference framework and in studying theoretical properties of methods we develop.  

Some highlight application areas: 
(1) Modeling of biological communities and biodiversity - we are considering global data on fungi, insects, birds and animals including DNA sequences, images, audio, etc.  Data contain large numbers of species unknown to science and we would like to learn about these new species, community network structure, and the impact of environmental change and climate.

(2) Brain connectomics - based on high resolution imaging data of the human brain, we are seeking to developing new statistical and machine learning models for relating brain networks to human traits and diseases.

(3) Environmental health & mixtures - we are building tools for relating chemical and other exposures (air pollution etc) to human health outcomes, accounting for spatial dependence in both exposures and disease.  This includes an emphasis on infectious disease modeling, such as COVID-19.

Some statistical areas that play a prominent role in our methods development include models for low-dimensional structure in data (latent factors, clustering, geometric and manifold learning), flexible/nonparametric models (neural networks, Gaussian/spatial processes, other stochastic processes), Bayesian inference frameworks, efficient sampling and analytic approximation algorithms, and models for "object data" (trees, networks, images, spatial processes, etc).

Contact Info:
Office Location:  218 Old Chemistry Bldg, Durham, NC 27708
Office Phone:  (919) 684-8025
Email Address: send me a message
Web Pages:

Office Hours:

Thurs 9-10am

Ph.D.Emory University1997
PhDEmory University1997
B.S.Pennsylvania State University1994

Bayesian Statistics
Complex Hierarchical and Latent Variable Modelling
Nonparametric Statistical Modelling
Model Selection
Statistical Modeling
Research Interests: Nonparametric Bayes, Latent variable methods, Model uncertainty, Applications in epidemiology & genetics, Machine learning

Current projects: Nonparametric Bayes methods for conditional distributions, Semiparametric methods for high-dimensional predictors, New priors for functional data analysis, Borrowing information across disparate data sources, Methods for identifying gene x environmental interactions

Development of Bayesian methods motivated by applications with complex and high-dimensional data. A particular focus is on nonparametric Bayes approaches for conditional distributions and for flexible borrowing of information. I am also interested in methods for accommodating model uncertainty in hierarchical models, and in latent variable methods, including structural equation models. A recent interest has been in functional data analysis.

Areas of Interest:

Functional data analysis
Latent variable methods
Machine learning
Molecular epidemiology
Nonparametric Bayes
Order restricted inference
Model selection and averaging


Action Potentials • Algorithms • Artificial Intelligence • B-Lymphocytes • Bayes Theorem • Computer Simulation • Data Interpretation, Statistical • DNA-Binding Proteins • Electrophysiological Phenomena • Epidemiologic Methods • Gene Dosage • Genetic Association Studies • Germinal Center • Longitudinal Studies • Markov Chains • Models, Statistical • Models, Theoretical • Monte Carlo Method • Multivariate Analysis • Neurons • Pattern Recognition, Automated • Phenotype • Probability • Stochastic differential equations

Representative Publications   (More Publications)   (search)

  1. Dunson, DB, Nonparametric Bayes local partition models for random effects., Biometrika, vol. 96 no. 2 (January, 2009), pp. 249-262, ISSN 0006-3444 [doi]  [abs]
  2. Bigelow, JL; Dunson, DB, Bayesian semiparametric joint models for functional predictors., Journal of the American Statistical Association, vol. 104 no. 485 (January, 2009), pp. 26-36, Informa UK Limited, ISSN 0162-1459 [doi]  [abs]
  3. Dunson, DB; Xing, C, Nonparametric Bayes Modeling of Multivariate Categorical Data., Journal of the American Statistical Association, vol. 104 no. 487 (January, 2012), pp. 1042-1051, ISSN 0162-1459 [doi]  [abs]
  4. Dunson, DB; Park, JH, Kernel stick-breaking processes, Biometrika, vol. 95 no. 2 (June, 2008), pp. 307-323, Oxford University Press (OUP), ISSN 0006-3444 [doi]  [abs]
  5. Dunson, DB; Herring, AH; Engel, SM, Bayesian selection and clustering of polymorphisms in functionally related genes, Journal of the American Statistical Association, vol. 103 no. 482 (June, 2008), pp. 534-546, Informa UK Limited, ISSN 0162-1459 [doi]  [abs]
Recent Grant Support

  • A Planetary Inventory of Life - a New Synthesis Built on Big Data Combined with Novel Statistical Methods, European Research Council, 2020/04-2026/03.      
  • Duke University Program in Environmental Health, National Institutes of Health, 2013/07-2024/06.      
  • Calibrated uncertainty quantification in statistical learning, Office of Naval Research, 2021/05-2024/05.      
  • HDR TRIPODS: Innovations in Data Science: Integrating Stochastic Modeling, Data Representation, and Algorithms, National Science Foundation, 2019/10-2022/09.      
  • Reproducibility and Robustness of Dimensionality Reduction, National Institutes of Health, 2017/09-2022/07.      
  • Structured nonparametric methods for mixtures of exposures, National Institutes of Health, 1R01-ES028804-01, 2018/03-2022/02.      
  • An Integrated Nonparametric Bayesian and Deep Neural Network Framework for Biologically-Inspired Lifelong Learning, Defense Advanced Research Projects Agency, 2018/02-2021/12.      
  • Probabilistic learning of structure in complex data, Office of Naval Research, N00014-17-1-2844, 2017/09-2021/08.      
  • CRCNS: Geometry-based Brain Connectome Analysis, National Institutes of Health, 1R01-MH118927-01, 2018/09-2021/06.      
  • Postdoctoral Training in Genomic Medicine Research, National Institutes of Health, 2017/06-2021/05.      
  • Scalable probabilistic inference for huge multi-domain graphs, Alibaba Innovative Research, 2017/11-2021/04.      
  • BIGDATA:F: Scalable Bayes uncertainty quantification with guarantees, National Science Foundation, 1546130, 2015/11-2020/10.      
  • BIGDATA:F: Scalable Bayes uncertainty quantification with guarantees, National Science Foundation, 1546130, 2015/11-2020/10.      
  • Predicting Performance from Network Data, U.S. Army Research Institute for the Behavioral and Social Sciences, W911NF-16-1-0544, 2016/09-2020/09.      
  • New methods for quantitative modeling of protein-DNA interactions, National Institutes of Health, 2015/09-2020/08.      
  • Network motifs in cortical computation, University of California - Los Angeles, 1430 G UA755, 2016/09-2019/06.      
  • Network motifs in cortical computation, University of California - Los Angeles, 1430 G UA755, 2016/09-2019/06.      
  • Nonparametric Bayes Methods for Big Data in Neuroscience, National Institutes of Health, 2014/09-2019/06. 
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320