Causal-Inference

Directed mixed graphs permit directed and bidirected edges between any two vertices. They were first considered in the path analysis developed by Sewall Wright and play an essential role in statistical modeling. We introduce a matrix algebra for …

We apply ideas from post-selection inference to randomization tests for adaptive experiments.

A new Bayesian full-information method for life-course Mendelian randomization

We propose a systematic way to select confounders

By combining causal graphs and randomization inference, a formal justification for Mendelian randomization is given in the context of with-family studies.