Portugu√™s          English

Research

On my postdoc, I worked on devoloping statistical methods to infer the location of Twitter users, based on their friends' location and their posts.

During my PhD, I worked with imputation methods for confidential and missing data, with aplication on social sciences and adaptive survey design.

In one of my PhD projects, we developed an imputation method for multivariate continuous variables when there is missing not at random data. We fit a Dirichlet process mixture of multivariate normals to the observed data under a Bayesian framework to provide flexibility. We provide some guidelines on how to alter the estimated distribution using the posterior samples of the mixture model and obtain imputed data under different scenarios.

I also worked on Imputation of Confidential Datasets with Spatial Locations using Point Process Models. We suggest a method to generate synthetic data sets with imputed spatial locations, respecting individuals' confidentiality without losing statistical utility. Using Bayesian spatial point models, we generate imputed data sets for public release.

I also worked on a consulting project with researchers from the Evolutionary Anthropology Department at Duke University. We modelled the relationship of agression and paternity rates between pairs of chimpanzees.

On my master's thesis, I worked on a space-time surveillance method for point processes. We propose a surveillance method that uses cumulative surfaces to determine when and where a cluster is emerging.

Papers

[1] Thais Paiva and Jerome P. Reiter. Stop or continue data collection: A nonignorable missing data approach for continuous variables. Journal of Official Statistics, 33(3):579-599, 2017. [ bib | DOI | http ]
[2] Thais Paiva, Avishek Chakraborty, Jerry Reiter, and Alan Gelfand. Imputation of confidential data sets with spatial locations using disease mapping models. Statistics in Medicine, 33(11):1928-1945, 2014. [ bib | DOI | http ]
[3] Thais Paiva, Renato Assunção, and Taynãna Simões. Prospective space-time surveillance with cumulative surfaces for geographical identification of the emerging cluster. Computational Statistics, 30(2):419-440, 2015. [ bib | DOI | http ]
[4] Aline Piroutek, Renato Assunção, and Thais Paiva. Space-time prospective surveillance based on knox local statistics. Statistics in Medicine, 33(16):2758-2773, 2014. [ bib | DOI | http ]
[5] Joseph T. Feldblum, Emily E. Wroblewski, Rebecca S. Rudicell, Beatrice H. Hahn, Thais Paiva, Mine Cetinkaya-Rundel, Anne E. Pusey, and Ian C. Gilby. Sexually coercive male chimpanzees sire more offspring. Current Biology, 24(23):2855 - 2860, 2014. [ bib | DOI | http ]

This file was generated by bibtex2html 1.95.