Statistics and Data Science Seminar: "K sample Multiplier Bootstrap CLT with applications to High Dimensional MANOVA"

Speaker: Nilanjan Chakraborty, Michigan State University

Abstract: This talk mainly concerns about a K sample High Dimensional CLT over a class of Hyper-Polygons. This result finds an extremely useful application in the context of High Dimensional MANOVA problem based on supremum type test statistics for the difference in means among the K groups. Here we can allow the number of groups(K) to diverge to infinity. The test procedure considered here is free from any distribution and correlational assumptions which broadens its scope towards practical applications. The problem of Linear Hypothesis testing for a MANOVA problem has also been tackled using the previously mentioned CLT result. The asymptotic analysis of these tests in terms of controlling Size and Power has been theoretically validated. Brief simulation study has been done which corroborates the findings done in the theoretical sections. This is a joint work with Prof. Lyudmila Sakhanenko.

Hosts: Likai Chen and Debashis Mondal