This is RSSNI's second talk in 2024
RSSNI - Talk on Wednesday, February 21st, 2024 at 1pm GMT
Dear Fellows
I am delighted to alert you to our second talk of 2024 on heterogeneous treatment effects in RCTs by Brieuc Lehmann of University College London. This will be a hybrid event using MS Teams software
(link) with the speaker on-line and an in-person audience in Room 017 on the second floor of the Peter Froggatt Centre in the main quadrangle, QUB (
link).
Title
Fusing experimental and observational data with multi-task Gaussian processes to estimate heterogeneous treatment effects
Abstract
Randomised control trials (RCT) are widely considered the gold standard for making causal predictions and assessing treatment effects, due to the internal validity guaranteed from randomisation. However, the strict eligibility criteria lead to small samples not representative of the target population and as a result to lack of external validity. In contrast, observational studies, which typically come in larger sample sizes, are often more representative of the target population, but lack internal validity due to confounding leading to biased results. In this talk, I will present a Bayesian non-parametric approach to obtain estimates of heterogeneous treatment effects for the target population. Our approach is based on multi-output Gaussian Processes, where the limited RCT observations are used to correct the confounding effect on the observational data.
All welcome (including non-Fellows).
Previously recorded RSSNI talks
here.
RSSNI talk write-ups here
Gilbert MacKenzie
Hon. Sec (Meetings) and
Felicity Lamrock
Meetings Host
RSSNI
Dr. Brieuc Lehmann UCL, London, UK
Gilbert MacKenzie
gilbert.mackenzie.cbs@gmail.com