Research Interests
Markov chain Monte Carlo; Bayesian methods, including
non/semi-parametric Bayesian methods, and Bayesian methods in
biostatistics and in machine learning; and survival analysis
Selected Papers Since 2010
- Doss, H., and Hobert, J.P. (2010). Estimation of Bayes
factors in a class of hierarchical random effects models using a
geometrically ergodic MCMC algorithm.
[PostScript]
[PDF]. (This has appeared in Journal
of Computational and Graphical Statistics, 19
295-312.)
- Doss, H. (2010). Estimation of large families of Bayes
factors from Markov chain output.
[PostScript]
[PDF]. (This has appeared in Statistica
Sinica, 20 537-560.)
- Buta, E. and Doss, H. (2011). Computational approaches for
empirical Bayes methods and Bayesian sensitivity analysis. [PostScript] [PDF]. (This has
appeared in The Annals of Statistics, 39
2658-2685.)
- Doss, Hani (2012). Hyperparameter and model selection for
nonparametric Bayes problems via Radon-Nikodym derivatives. [PostScript] [PDF]. (This has
appeared in Statistica Sinica, 22 1-26.)
- Doss, H. and Tan, A. (2014). Estimates and standard errors
for ratios of normalizing constants from multiple Markov chains
via regeneration.
[PostScript]
[PDF]. (This has appeared in Journal of the
Royal Statistical Society, Series B, 76 683-712.)
- Tan, A., Doss, H. and Hobert, J.P. (2015). Honest importance
sampling with multiple Markov chains.
[PostScript]
[PDF]. (This has appeared in Journal
of Computational and Graphical Statistics, 24
792-826.)
- George, C.P. and Doss, H. (2018). Principled selection of
hyperparameters in the latent Dirichlet allocation model. [Main Paper PostScript]
[Supplement
PostScript] [Main
Paper PDF]
[Supplement PDF]. (This has appeared in Journal
of Machine Learning Research, 24 No. 162, 1-38.)
- Doss, H. and Park, Y. (2018). An MCMC approach to empirical
Bayes inference and Bayesian sensitivity analysis via empirical
processes.
[PostScript]
[PDF]. (This has appeared in The Annals of
Statistics, 46 1630--1663.)
- Chen, Z. and Doss, H. (2018). Inference for the number of
topics in the latent Dirichlet allocation model via Bayesian
mixture modelling. [Main
Paper PostScript]
[Supplement PostScript] [Main Paper PDF]
[Supplement
PDF]. (This has appeared in Journal of
Computational and Graphical Statistics, 28 567--585.)
- Xia, W. and Doss, H. (2020). Scalable hyperparameter
selection for latent Dirichlet allocation. [Main Paper PDF] [Supplement PDF].
(This has appeared in Journal of Computational and Graphical
Statistics, 29 875--895.)
- Yang, C.-H., Doss, H. and Vemuri, B. (2020). An empirical
Bayes approach to shrinkage estimation on the manifold of
symmetric positive-definite matrices.
[Main Paper PDF] [Supplement PDF].
(This has appeared in Journal of the American Statistical
Association, 119 259--272.)
- Doss, H. and Linero, A. (2024+). Scalable empirical Bayes
inference and Bayesian sensitivity analysis. [Main Paper PDF] [Supplement PDF].
(This will appear in Statistical Science.)
Software
- bsa Software
for dynamic visualization of changing prior and posterior in
Bayesian nonparametric analysis of censored data. This is joint
work with B. Narasimhan.
- mc-mdp-surv
Software for Monte Carlo methods for Bayesian analysis of
survival data using mixtures of Dirichlet process priors
(JCGS 2003, 282-307). This is joint work with Fred
Huffer.