My research focuses on Bayesian statistical methods.  I am interested in both the development of new  methodologies and their application in a wide range of disciplines such as health sciences, computational biology, political science, finance and engineering.  Below is a more detailed description of my research interests with a list of relevant publications and grants that have supported my work.

Statistical Methodology:   From a methodological perspective, my early work focused on the development of nonparametric Bayesian models, which aim at minimizing the number of assumptions in an statistical analysis by defining prior distributions over large collections of models.  I am also interested in objective and robust Bayesian analysis (how to derive prior distributions that have either minimal or bounded impact on the final results), and in "object-oriented" statistics (the analysis of complex objects such as functions or graphs).  Some of my work on network models has been supported by the Defense Advanced Research Projects Agency (DARPA), which awarded me a Young Faculty Award in 2010.

Rodriguez, A. and Quintana, F. A. (2014). On species sampling sequences induced by residual allocation models.  Journal of Statistical Planning and Inference,  157: 108-120.    

Rodriguez, A. (2013).  On the Jeffreys prior for the multivariate Ewens distribution.  Statistics and Probability Letters, 83: 1539-1546.

Dobra, A., Lenkoski, A. and Rodriguez, A. (2011). Bayesian inference for general Gaussian graphical models with application to multivariate lattice data.  Journal of the American Statistical Association, 106: 1418-1433.    

Rodriguez, A. and Dunson, D. B. (2011). Nonparametric Bayesian models through probit stick-breaking processes. Bayesian Analysis, 6: 145-178.

Rodriguez, A., Dunson, D. B. and Gelfand, A. E. (2008).  The Nested Dirichlet Process (with Discussion).  Journal of the American Statistical Association, 103: 1131-1144.

Computational Methods:  I am interested in computational methods for Bayesian models.  In addition to Markov chain Monte Carlo algorithms, I am also interested in sequential Monte Carlo and stochastic search methods.  I recently joined the team behind NIMBLE, where I am working on extending the environment so that it can manage nonparametric models based on Dirichlet and Gaussian processes.  This work has received support from the National Science Foundation (award #1622444) and the UCSC Center for Research in Open Source Software.

Mukherjee, C. and Rodriguez, A. (2016).  GPU-powered Shotgun Stochastic Search for Dirichlet process mixtures of Gaussian Graphical Models.  Journal of Computational and Graphical Statistics, 25: 762-788.

Rodriguez, A. (2011) On-line inference for the infinite hidden Markov model. Communications in Statistics: Simulation and Computation, 40: 879-893.

Biostatistics and Computational Biology:  I am interested in the application of statistical methods in biological and health sciences.  My work on biostatistics has focused on modeling Receiver Operating Caractheristic (ROC) curves for medical tests, partly due to my tenure as a permanent member of the Cancer Biomarker Study Section of the National Institutes of Health.  I am also interest in epidemology, particularly in disease mapping and clustering.  In terms of computational biology, I have an interested in structural proteomicss and models of molecular evolution.  Some of this work has been funded by the National Institutes of Health (award # 5R01GM090201).

Rodriguez, A. and Martinez, J. C. (2014).  Bayesian semiparametric estimation of covariate-dependent ROC curves.  Biostatistics, 15: 353-369.

Rodriguez, A. and Dunson, D. B. (2014). Functional clustering in nested designs:  Modeling variability in reproductive epidemiology studies.  Annals of Applied Statistics, 8: 1416-1442.

Wang, H. and Rodriguez, A. (2014). Identifying pediatric cancer clusters in Florida using loglinear models and generalized lasso penalties.  Statistics and Public Policy, 1: 86-96.

Rodriguez, A. and Schmidler, S. C. (2014).  Bayesian Protein Structure Alignment.  Annals of Applied Statistics, 8: 2068-2095.

Datta, S., Pradro, R. and Rodriguez, A. (2013).  Bayesian factor models in characterizing molecular adaptation.  Journal of Applied Statistics, 40: 1402-1424.

Datta, S., Rodriguez, A. and Prado, R.  (2012). Bayesian Semiparametric Regression Models to Characterize Molecular Evolution.  BMC Bioinformatics, 13: 278.

Datta, S., Prado, R., Rodriguez, A. and Escalante, A. (2011). Characterizing molecular adaptation: a hierarchical approach to assess the selective influence of amino acid properties.  Bioinformatics, 26: 2818-2825.    

Political Science:  I am interested in models for revealed preferences that relax some of the typical assumptions used in the literature, such as ignorable missingness and invariance of preferences.

Lofland, C. L., Rodriguez, A. and Moser, S. (2017). Assessing differences in legislators’ revealed preferences: A case study on the 107th US Senate. The Annals of Applied Statistics, 11: 456-479.

Rodriguez, A. and Moser, S. (2015). Measuring and accounting for strategic abstentions in the U.S. Senate, 1989-2012.  Journal of the Royal Statistical Society, Series C, 64: 779-797.

Finance and Econometrics:  I have done some work on stochastic volatility and structural credit risk models.  I am also interested in derivative pricing.

Garay, U., ter Horst, E., Molina, G., and Rodriguez, A. (2016). Bayesian Nonparametric Measurement of Factor Betas and Clustering With Application to Hedge Fund Returns.  Econometrics, 4: 13. 

Rodriguez A., ter Horst, E. and Malone, S. (2014). Bayesian Inference for a Structural Credit Risk Model with Stochastic Volatility and Stochastic Interet Rates.  Journal of Financial Econometrics, 13: 839-867.

Ter Horst, E., Rodriguez, A., Gzyl, H. and Molina, G. (2012). Stochastic Volatility Models Including Open, Close, High and Low Prices. Quantitative Finance, 12: 199-212.

Engineering:  My interests in engineering focus on two areas.  On one hand, I am interested in applied control, particularly in how statistical methods can be used to derive control algorithms in uncertain environments.  I am also interested in human mobility models, particularly from the point of view of computer network design.  Some of this work has been funded by the National Science Foundation (award #1321151) and the National Aeronautics and Space Administration. 

Hening, S., Regueiro, P., Rodriguez, A., Teodorescu, M., Nguyen, N. T., and Corey A.  (2015) Bayesian Modeling for Decentralized UAV Control and Task Allocation.  AIAA Infotech @ Aerospace. Kissimmee, Florida.

Song, S., Rodriguez, A. Teodorescu, M. (2015). Trajectory planning for autonomous nonholonomic vehicles for optimal monitoring of spatial phenomena. International Conference on Unmanned Aircraft Systems (ICUAS). Denver, Colorado.

Nunes, B., Rodriguez, A. and Obraczka, K. (2012) “SAGA: Socially- And Geography-Aware Mobility Modeling Framework,” The 15th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems, MSWIM’12