Talks

2024

Design: The Elusive Principle of Statistics

Sensitivity analysis for observational studies: past, present, and future

Confounder selection via iterative graph expansion

2023

Sensitivity analysis via stochastic programming

Confounder selection via iterative graph expansion

Almost exact Mendelian randomization

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

Simultaneous hypothesis testing using negative controls

Negative control is a common technique in scientific investigations and broadly refers to the situation where a null effect (“negative …

2022

The randomization principle in causal inference: A modern look at some old ideas

Randomization is a fundamental principle in causal inference and was first proposed by R A Fisher about a century ago. Although …

A crash course on causal inference

Multiple conditional randomization tests

Two High-Profile Examples of Selection Bias

This talk will examine the selection bias that occurred in studying some most contentious problems. In the first case study, we will …

Fisher, Statistics, and Randomization

One of Fisher’s most important scientific contributions is the paradigm of randomized experiments. I will try to trace the origin of …

How infectious was COVID-19 when it first circulated in Wuhan?

This is given to A-level students.

What is a randomization test?

2021

Multiple conditional randomization tests

Reliable Inference for Precision Medicine

Two central objectives of individualized treatment are precision and optimality. A third objective is robustness, and this talk aims to …

BETS: The dangers of selection bias in early analyses of the coronavirus disease (COVID-19) pandemic

The coronavirus disease 2019 (COVID-19) has quickly grown from a regional outbreak in Wuhan, China to a global pandemic. Early …

Mendelian randomization: Old and new insights

Mendelian randomization (MR) is a method for causal inference that utilizes the natural experiment in genetic inheritance. The idea of …

Mendelian randomization: Old and new insights

Mendelian randomization (MR) is a method for causal inference that utilizes the natural experiment in genetic inheritance. The idea of …

Discussion on 'Causal Inference in Genetic Trio Studies'

Discussion on Dr Stephen Bates’ talk in the Online Causal Inference Seminar.

2020

Selection bias in 2020

This talk will examine the selection bias that occurred in studying some most contentious problems in 2020. In the first case study, we …

Discovering mechanistic heterogeneity using Mendelian randomization

Mendelian Randomization (MR) is a popular method in epidemiology and genetics that uses genetic variation as instrumental variables for …

Sensitivity analysis for observational studies

Sensitivity analysis is widely recognized as a critical step in an observational study but is seldom found in applications. One reason …

Using sparsity to overcome unmeasured confounding

Sparsity is often used to improve the interpretability of a statistical analysis and/or reduce the variance of a statistical estimator. …

Bootstrapping sensitivity analysis

Causal inference: An introduction

Introduction to causal inference for social science PhD students.

The cycle of statistical research

More than fifty years ago, John Tukey first envisioned a field we now call “Data Science” (he called it “Data …

2019

Using sparsity to overcome unmeasured confounding: Two examples

Sparsity is often used to improve the interpretability of a statistical analysis and/or reduce the variance of a statistical estimator. …

MR Data Challenge 2019

This report entered the 2019 MR Data Challenge and contains reproducible R code for our analysis.

The statistics of summary-data Mendelian randomization

Invited talk giving an overview of my research on summary-data Mendelian randomization.

Mendelian randomization: A tutorial

Tutorial talk for the theory, methods, and practice of Mendelian randomization.