Title:  To be confirmed
Date:  Friday, 30 June, 2017
Time:  14.00 - 15.00
Venue:  Seminar Room, OS6, Second Floor Oakfield House
Chair:  George Davey Smith

Johannes Textor
Radboud University Medical Centre, Nijmegen

Biography

I obtained my PhD in Theoretical Computer Science at the University of Luebeck, Germany, in 2011, and then joined the Theoretical Biology group at Utecht University, the Netherlands, as a postdoctoral fellow. In 2015, I started a tenure track at Carl Figdor's Tumor Immunology group in Nijmegen, the Netherlands.

In 2011, I came across Judea Pearl's work on structural causal models (SCM). Ever since, I have been intrigued by its algorithmic and statistical aspects. I created the software "dagitty.net", an interactive program to build and analyze SCMs, that has since been adopted by both instructors and researchers worldwide. In Spring 2016, I collaborated with Judea Pearl to provide interactive and programmatic exercises for his new book "Causality in Statistics: A Primer" (with Maria Glymour and Nicholas Jewell), and the accompanying R package ‘dagitty’ has been released together with the book in March 2016. My research on the algorithmic aspects of SCM has won a young investigator's award from the German Society of Epidemiology in 2012, and an IBM-sponsored award at the Uncertainty in Artificial Intelligence conference in 2014.

DAGitty

Textor J. et al. Robust causal inference using directed acyclic graphs: the R package ‘dagitty’ IJE 2016:1887-1894 (https://academic.oup.com/ije/article-lookup/doi/10.1093/ije/dyw341)

Abstract from above article

Directed acyclic graphs (DAGs), which offer systematic representations of causal relationships, have become an established framework for the analysis of causal inference in epidemiology, often being used to determine covariate adjustment sets for minimizing confounding bias. DAGitty is a popular web application for drawing and analysing DAGs.

Here we introduce the R package ‘dagitty’, which provides access to all of the capabilities of the DAGitty web application within the R platform for statistical computing, and also offers several new functions. We describe how the R package ‘dagitty’ can be used to: evaluate whether a DAG is consistent with the dataset it is intended to represent; enumerate ‘statistically equivalent’ but causally different DAGs; and identify exposure outcome adjustment sets that are valid for causally different but statistically equivalent DAGs. This functionality enables epidemiologists to detect causal misspecifications in DAGs and make robust inferences that remain valid for a range of different DAGs. The R package ‘dagitty’ is available through the comprehensive R archive network (CRAN) a [https://cran.r-project.org/web/packages/dagitty/]. The source code is available on github at [https://github.com/jtextor/dagitty]. The web application ‘DAGitty’ is free software, licensed under the GNU general public licence (GPL) version 2 and is available at [http://dagitty.net/].