-By Taruna Rapaka
Gaurav Agarwal, a Ph.D. candidate in statistics and member of KAUST Associate Professor Ying Sun's Environmental Statistics (ES) research group, recently won an American Statistical Association (ASA) Student Paper Award sponsored by the Sections on Computing and Graphics (SCSG). In addition to his ASA SCSG award, Agarwal has also been selected a Distinguished Student Paper Award winner by the Eastern North American Region (ENAR) of the International Biometric Society for his paper titled "Flexible Quantile Contour Estimation for Multivariate Functional Data: Beyond Convexity."
JSM 2021 is one of the largest statistical events worldwide, with over 600 sessions and 6,500 attendees from 52 countries. This year's event will focus on a broad range of topics, from statistical applications to methodology and theory to the expanding boundaries of statistics and data science. The ASA award will be presented at the mixer for the section on SCSG at JSM 2021.
The ENAR 2021 Spring Meeting brings together researchers and practitioners from academia, industry, and government, connected through a common interest in biometry. Each year up to twenty Distinguished Student Paper Awards are presented at the event. Agarwal will receive his award at the beginning of the ENAR President's Invited Address session.
“I am thrilled to receive the student paper award from the ASA and a Distinguished Student Paper Award from the ENAR of the International Biometric Society,” Agarwal said. “I feel honored that our research was recognized globally by the statistical community, and I feel motivated to do more interesting research projects in the future.”
“In this paper, we compute quantiles of multivariate data varying over time arising in all areas of science, medicine, and engineering. Computing quantiles is essential for data analysis; however, the extension of quantiles to this form of high-dimensional data is quite challenging.”
“We proposed a flexible model to estimate quantiles for multivariate data over time, which can visualize data with complex shapes and provide valuable summaries like median. When the method is applied to air pollution data analysis, it highlights the problem of describing the two variable distributions of PM2.5 (particulate matter) and geopotential height at 850 hPa. However, despite the non-convex and flexible shape of the bivariate distribution, the method allows to capture its dynamics over time,” he explained.
Pursuing inspirational research at KAUST
Before joining KAUST in the fall of 2016, Agarwal obtained his bachelor’s degree in statistics from Hindu College, Delhi, and a master’s degree in statistics from the Indian Institute of Technology (IIT), Kanpur. His previous research work at KAUST, which did not focus on a multivariate distribution’s flexible shapes, prompted him to choose his current research topic.
Agarwal believes that the continuous guidance and support of his supervisor Professor Ying Sun, and KAUST’s excellent research environment, have considerably impacted his success in developing novel approaches in his research.
“I feel that these awards reflect the guidance of my advisor, Prof. Sun. She helped me design this project, and her inspiring ideas and advice helped me build this research. I am grateful for the excellent resources provided by KAUST, which creates an ideal environment for conducting research,” he concluded.