Abstract

Recent scientific advancements in technologies give rise to voluminous data in various fields, including biology, finance, business, health care systems, and government resource managements, to name a few. The call of the hour goes toward the (bio)statisticians/data-scientists to develop novel methods/computer algorithms to analyze and extract sensible meanings out of these high-/ultrahigh-dimensional data that pose challenges such as computational burden, statistical inaccuracy, and algorithmic instability. Specifically, a major daunting task is to discover authentic causal connections, if any, of these collected data to the outcome(s) of interest. Good news is that contemporary statistical/computational developments have started to successfully fathom answers to such challenges in data related to high-dimensional causal inference using tools such as machine learning and deep learning. Consequently, the basic scientists have started to perceive a holistic understanding of the intricate one-to-one relationships and mechanisms of the study phenomenon of interests.

This invited paper session incorporates topics on cutting-edge statistical developments on high-dimensional causal inference, including a scientific discussion on the presented topics at the end. Moreover, the four speakers and the discussant (see list below) represent a notable mix of gender, experience-level, and geographical regions.