Martina Pavlicova, PhD, MS

Visiting Associate Professor, AUA Turpanjian College of Health Sciences (CHS), Associate Professor, Biostatistics at the Columbia University Irving Medical Center (CUMC)

PhD, MS, Ohio State University
MS, Charles University, Czech Republic

 Dr. Martina Pavlicova is Associate Professor of Biostatistics at Columbia University Irving Medical Center. She teaches courses about Applied Regression, Categorical Data Analysis, Introduction to Health Data Science in Mailman School of Public Health. She is a director of the Statistics, Assessment and Data Management core within HIV Center for Clinical and Behavioral Studies at the New York State Psychiatric Institute (NYSPI) and Columbia University. Additionally, she is a senior/head biostatistician in the Division of Behavioral Medicine, CUIMC, Columbia University, in Substance Abuse Center at Division on Substance Use at NYSPI, and also in NIDA Clinical Trials Network, Greater New York Node. Dr. Pavlicova is additionally active member of the Biostatistics, Epidemiology, and Research Design (BERD) in the Irving Institute for Clinical and Translational Research in CUIMC.

 Dr. Pavlicova has a long-standing interest in effective modern teaching methods for statistics and biostatistics and in methods of successful collaborations. As a recipient of many teaching awards (2016 Presidential Teaching Award, 2010 Early Career Teaching Award) and member of some prestigious societies (Glenda Garvey Teaching Academy, ASPH/Pfizer Health Academy of Distinguished Teachers), she pioneers innovative modern methods of team-based and self-directed learning methods in her classroom. In her collaborations, she utilizes modern management approaches to direct small to medium-sized teams of master-level statisticians located within large collaborative centers.

Dr. Pavlicova methodological research include analysis clinical trials data, longitudinal analysis of non-normally distributed data, multiple comparison procedures and statistical methods for analysis of functional MRI images. To  solve a multiple comparison issue when analyzing fMRI images, she developed Enhanced P-value Adaptive Thresholding procedure (EPAT) that applies adaptively false discovery rate to images in wavelet space while accounting for their specific spatial neighborhood structure and distribution. She is currently interested in methods of machine learning and their application in large datasets. Dr. Pavlicova additionally led papers introducing advanced statistical methodologies in fields of substance abuse or HIV, and has been the primary or senior biostatistician on numerous clinical trials.