Plenary Speakers


President's Invited Speaker


Stephen Senn, Competence Centre for Methodology and Statistics, Luxembourg Institute of Health


The Revenge of RA Fisher: Thoughts on Randomgate and its Wider Implications

Monday 10th, 9.30 h.

Room: Auditorio

Anastasios Tsiatis


Stephen Senn has worked as a statistician but also as an academic in various positions in Switzerland, Scotland, England and Luxembourg. Since 2011 he has been head of the Competence Center for Methodology and Statistics at the Luxembourg Institute of Health in Luxembourg. He is the author of Cross-over Trials in Clinical Research (1993, 2002), Statistical Issues in Drug Development (1997, 2007), Dicing with Death (2003) and in 2009 was awarded the Bradford Hill Medal of the Royal Statistical Society. He is an honorary life member of PSI and ISCB.



Abstract: RA Fisher warned us years ago: as ye randomize so shall ye analyse. We ignored him and we haven't faithfully  reflected the way we randomise in the way we analyse. In the pharmaceutical industry, we randomise in permuted blocks but we don't fit the block. Ex pharma researchers minimise but don't condition on the order of patients in the trial.

A recent interesting and heroic analysis by John Carlisle has identified dozens of clinical trials in leading journals as being either suspiciously imbalanced at baseline or having balance that's too good to be true. However, he analyses the baseline distributions as if the trials were completely randomized but nearly all trial are not. I consider Carlisle's analysis not only as regards whether or not the whole world of clinical trials is awash with fraud but also as regards the implication for analysis of outcomes, even if it is not.


I conclude that because we have arrogantly assumed that in theory we can do better than Fisher, in practice we often do worse.


Carlisle, J. B. "Data fabrication and other reasons for non‐random sampling in 5087 randomised, controlled trials in anaesthetic and general medical journals." Anaesthesia (2017).



Keynote Speaker


Francesca Dominici, Harvard University, USA


Model Uncertainty and Covariate Selection in Causal Inference

Wednesday 12th, 11.00 h.

Room: Auditorio

Francesca Dominici


Dr. Francesca Dominici is Professor of Biostatistics, Senior Associate Dean for Research, and Associate Dean of Information Technology at the Harvard T.H. Chan School of Public Health (USA). Her research focuses on the development of statistical methods for the analysis of large and complex data. She leads several interdisciplinary groups of scientists with the ultimate goal of addressing important questions in environmental health science, climate change, comparative effectiveness research, and health policy. 




Abstract: Researchers are being challenged with decisions on how to control for a high dimensional set of potential confounders in the context of a single binary treatment (e.g, drug) and in the context of a multivariate exposure vector with continuous agents and their interactions (e,g, exposure to mixtures). Typically, for a binary treatment, a propensity score model is used to adjust for confounding, while the uncertainty surrounding the procedure to arrive at this propensity score model is often ignored. Failure to include even one important confounder will results in bias. We discuss how to overcome issue of confounding selection and model uncertainty in causal inference. Specifically, we introduce the model averaged double robust (MA-DR) estimator, which accounts for model uncertainty in both the propensity score and outcome model through the use of model averaging. We also consider estimating the effect of a multivariate exposure that includes several continuous agents and their interactions when the true confounding variables are an unknown subset of a potentially large (relative to sample size) set of measured variables. We develop a new approach rooted in the ideas of bayesian model averaging to prioritize confounders among a high-dimensional set of measured covariates. We introduce a data-driven, informative prior that assigns to likely confounders a higher probability of being included into a regression model for effect estimation. We illustrate the performance of these estimators and applications to comparative effectiveness research and environmental problems.






 Technical Secretariat: Orzán Congres  


 Phone: +34 981 900 700 | Email: | Web:




© 2016 SERGLO - All rights reserved