Marianthi Markatou

PhD

Marianthi Markatou

PhD

Marianthi Markatou

PhD

Research Topics

Statistical Sciences (Statistics and Biostatistics): robustness, theory (& applications) of statistical distances, mixture models, model assessment, classification & clustering, machine learning, kernel methods, foundation of "big data" analysis. Interdisciplinary: text mining, biomedical informatics, safety of medical products, data science methods, comparative effectiveness.

Contact Information

726 Kimball Tower

Buffalo NY, 14214

Phone: (716) 829-2894

Fax: (716) 829-2200

markatou@buffalo.edu

Loading...

Selected Publications

  • Markatou, M., Chen, Y., Afendras, G. and Lindsay, B.G. (2016). Statistical Disances and their Role in Robustness. Technical Report.
  • Golzy, M., Markatou, M., and Shivram, A. (2016). Algorithms for Slustering on the Sphere: Advances and Applications.  Accepted. ICMLDA 2016.
  • Afendras, G. and Markatou, M. (2016). Uniform integrability of the OLS estimators, and the convergence of their moments.  Test, 25, 775-784.
  • Afendras, G. and Markatou, M. (2016). Optimality of Training/Test Size and Resampling Effectiveness in Cross-Validation. Technical Report.
  • Foss, A., Markatou, M, Ray, B., Heching, A. (2016). A semi-parametric method for clustering mixed data. Machine Learning, 105(3), 419-458.
  • Markatou, M., Ball, R., Botsis, T., Nguyen, M. and Woo, E.J. (2015). A text mining system for large medical text datasets and corresponding medical text classification using informative feature selection. US Patent, no. 9,075,796.
  • Chen, X., Vexler, A. and Markatou, M. (2015). Empirical likelihood ratio confidence interval estimation of best linear combinations of biomarkers. Computational Statistics and Data Analysis, 82, 186-198.
  • Markatou, M.* and Ball, R. (2014). A pattern discovery framework for adverse event identification and inference. Statistical Analysis and Data Mining, 7(5), 352-367.    
  • Lindsay, B. G., Markatou, M. and Ray, S. (2014). Kernels, degrees of freedom and power properties of quadratic goodness-of-fit tests. Journal of the American Statistical Association, 109:505, 395-410.
  • Sun, J., Hu, J., Luo, D., Markatou, M., Wang, F., Ebadollahi, S., Steinhubl, S. E., Daar, Z. and Steward, W. F. (2012). Combining knowledge and data driven insights for identifying risk factors using electronic health records. Proceedings of AMIA2012, 901-910.
  • Luo, D*., Wang, F., Sun, J., Markatou, M*., Hu, J., Ebadollahi, S. (2012). Scalable orthogonal regression for low redundancy feature selection and its healthcare applications. Proceedings on the 12 SIAM Conference in Data Mining, 576-587.
  • Markatou, M.*, Kurrupumullage Don, P., Hu, J. Wang, F., Sun, J., Sorrentino, R. and Ebadollahi, S. (2012). Case-based reasoning in comparative effectiveness research. IBM Journal of Research and Development56(5), 4:1-4:12.
  • Dimova, R., Markatou, M., Talal, A.H. (2011).  A comparison of information methods for model selection in mixed effects models with application to data from a study of treatment of HCV.  Computational Statistics and Data Analysis, 55(9), 2677-2697.
  • Wang, X., Hricpsak, G., Markatou, M., Friedman, C. (2009).  Active computerized pharmacovigilance using natural language processing, statistics and electronic health records:  a feasibility study.  Journal of the American Medical Informatics Association, 1613, 338-345.
  • Lindsay, B.G., Markatou, M., Ray, S., Yang, K., Chen, S-C. (2008).  Quadratic Distances on Probabilities:  A Unified Foundation.  Annals of Statitics, 3612, 982-1006.
  • Markatou, M., Tian, H., Bisuas, S. and Hripcsak, G. (2005). Analysis of the variance of cross validation estimators of the generalization error of computer algorithms.  Journal of Machine Learning Research, 6, 1127-1168.
  • Markatou, M. (2000). Mixture models, robustness and the weighted likelihood methodology.  Biometrics, 56, 483-486.
  • Markatou, M., Basu, A. and Lindsay, B.G. (1998).  Weighted likelihood estimating equations with bootstrap root search.  Journal of the American Statistical Association, 93, 740-750.