Pramita Bagchi
Pramita Bagchi
Ph.D.
Assistant Professor
Full-time Faculty
School: Milken Institute School of Public Health
Department: Biostatistics and Bioinformatics
Contact:
Science & Engineering Hall
800 22nd Street, NW
Washington DC 20052
Dr. Bagchi is an assistant professor at the department of Biostatistics & Bioinformatics. She is
interested in developing computationally efficient statistical methodology for the analysis of
longitudinal, spatial and time series data with a focus on high dimensional and functional
observations. Some of the application areas she works in include climate science, protein
sequencing data, medical imaging data, etc.
Postdoctoral Researcher – Department of Mathematics, Ruhr Universitat Bochum, Germany,
2015 -- 2018
Doctor of Philosophy in Statistics, University of Michigan, Ann Arbor, 2015
Master of Statistics, Indian Statistical Institute, Kolkata, India, 2010
Bachelor of Statistics, Indian Statistical Institute, Kolkata, India, 2008
Functional Data
Spatial and Spatio-Temporal Data
Longitudinal and Time Series Data
High dimensional data
Dr. Bagchi’s research focuses on developing new methodology for analyzing high dimensional
dependent data.
Dependence is a natural phenomenon occurring in several real life scenario, specifically in data
observed over time or in a spatial context. Ignoring this underlying spatial and temporal
dependence structure leads to incorrect results for inference and prediction problems. The
severity of dependence may drastically affect the behavior of the estimators. Moreover, the
behavior of the observations may change over time or based on geographical location. It is
important to include any such structure affecting the data generating process in the model.
Data can be observed in both temporal and spatial context, and often both spatial and
temporal dependence affect each other. Dr. Bagchi is interested in such interesting dynamics of
data and modelling and analyzing them with minimal assumptions on the structure.
The other aspect of Dr. Bagchi’s research deals with analyzing high dimensional data. With the
advancement of modern technology, we have access to high dimensional and high-resolution
data. Some interesting examples include medical imaging such as EEG and fMRI, miRNA
sequencing data, satellite images, financial transaction data etc. Statistical analysis if these data
pose challenges both in terms of availability of mathematical tools to analyze them, as well as
computational cost to deal with the high dimensionality of the observations. Dr. Bagchi is
interested in developing computationally efficient statistical methodologies to analyze these
data especially in the context of dependence.
Dr. Bagchi’s research has been funded by the National Science Foundation and INOVA hospital.