July 5 - 10, 2020 in Seoul, Korea
Methodological issues in observational studies: promoting best analyses and relevant research
Preliminary Speakers and Titles:
1. Aris Perperoglou (Cambridge, UK) for TG2
'Towards state of tfor variable selection – research required!'
2. Els Goetghebeur (Gent, Belgium) for TG7
'Three causal lessons from our Simulation Learner: SUTVA is fiction; randomisation fails as an instrument for many post randomisation exposures, and averaging causal effects over an observed (experimental) instrument may be irrelevant'
3. James Carpenter (London, UK) for TG1
'Missing data: best practice and beyond in flexible modelling and causal inference'
4. Michal Abrahamowicz (Montreal, Canada) for the Simulation Studies panel
'Designing simulation studies for accurate, generalizable conclusions: recent developments'