An Efficient Computational Method for Causal Inference in High-Dimensional Data: Neighborhood-Based Cross Fitting


Media is loading

Document Type


Publication Date



About My Research: Current method suggests splitting data at least a thousand times to get reliable results. This is computationally expensive, especially for high-dimensional data (that is, data with a large number of variables relative to the sample size). I am using the structure of data as a shortcut for splitting; thus, the data is only required to be split twice. My method is ten times faster and achieves the same result as splitting the data a thousand times.

Why I’m participating in the 3MT: I'm participating in the 3MT event to communicate my research findings to the public. Specifically, to communicate my research to content experts who would find my method applicable to their research.

This document is currently not available here.