Prakash Borpatra Gohain
I am a Ph.D. student (Doktorand) at the Division of Information Science and Engineering (School of EECS). I started working from March 2018 under the supervision of Professor Magnus Jansson . Prior to that, I worked as a research scholar in the department of Signal Processing and Communication (SPCRC) at the International Institute of Information Technology-Hyderabad (IIIT-H), India. I received my Master of Science degree in Electronics and Communication from IIIT-H in 2017 (master's thesis).
My PhD research is primarily concerned with designing robust model selection methods for linear regression models, especially targeting the sample scarce scenario when the number of available measurements is small compared to the number of covariates/parameters. Selecting the best model from a subset of candidate models is a key ingredient in data analysis for reliable statistical inference. Therefore, it is central to scientific studies in many fields, such as economics, engineering, finance, science, marketing and biology. In this regard, we investigate the drawbacks of current classical methods and derive new robust methods using statistical methods that guarantee consistency as the sample size grows large and/or at high signal-to-noise-ratios.