Welcome to my website! My name is Matt Tudball and I am a Wellcome Trust 4-year PhD student at the MRC Integrative Epidemiology Unit, University of Bristol, and a visiting PhD student at the Statistical Laboratory, University of Cambridge. I am supervised by George Davey Smith, Kate Tilling, Qingyuan Zhao, Rachael Hughes and Jack Bowden.
My research involves the development of novel causal and statistical inference methods with application to genetic epidemiology.
Download my CV .
PhD in Statistical Genetics, 2022
MRC Integrative Epidemiology Unit, University of Bristol
MA in Economics, 2017
University of Toronto
BSc in Economics and Mathematics, 2016
University of Toronto
We provide a formal justification for the validity of the MR design by building a causal model which includes features such as assortative mating, linkage disequilibrium, population stratification and transmission ratio distortion. We then propose an “almost exact” randomization test for MR based on explicitly modelling the distribution of crossovers.
We develop an approach to statistical inference in stochastic optimization problems when both the function to minimized, and the set over which it is minimized, must be estimated empirically. We apply this inference procedure to the problem of selection bias in large population cohorts such as UK Biobank. We propose a sensitivity analysis which is able to flexibly incorporate a wide variety of population-level information, while providing valid statistical inference.
In MR studies, the exposure is often a coarsened approximation to some latent continuous trait. Genetically driven variation in the outcome can exist within categories of the exposure, violating the exclusion restriction. I derive a closed-form expression for the resulting bias and propose a simple correction that can be used with summary-level data to provide MR estimates with interpretable effect sizes.