송호승 연구실

Development of kernel-based methods for two-sample testing, change-point detection, and independence testing with applications to high-dimensional and non-Euclidean data.

Statistical methods for analyzing microbiome composition, differential association analysis, and handling batch effects in microbiome studies.

Statistical methods for analyzing high-dimensional data including genomic and spatial proteomics data with focus on clustering and feature identification.

Development of robust and scalable methods for detecting change-points in multivariate data with repeated measures and time series applications.