We meet to read one or more papers closely. Each meeting is summarised here: what the paper claimed, what we discussed, what stayed unresolved, and what we might read next. New members and visitors are welcome.
Next meeting
Tuesday 1 September 2026, 3:30 pm · Room 124, Building 184
Jiadong will discuss several papers that shaped how he thinks about the way causal questions are posed in causal inference.
- Swales J. The troublesome search for evidence: three cultures in need of integration. J R Soc Med 93(8):402–407 (2000). doi:10.1177/014107680009300804 — a high-level, somewhat philosophical discussion of what counts as scientific evidence.
- Lu H, Li F, Lesko CR, et al. Four targets: an enhanced framework for guiding causal inference from observational data. Int J Epidemiol 54(1) (2025). doi:10.1093/ije/dyaf003 — a review defining the key concepts in formulating a causal question from observational data.
- Dickerman BA, García-Albéniz X, Logan RW, Denaxas S, Hernán MA. Avoidable flaws in observational analyses: an application to statins and cancer. Nat Med 25(10):1601–1606 (2019). doi:10.1038/s41591-019-0597-x — a classic paper resolving an apparent conflict between observational studies and meta-analyses of trials by designing the causal task properly.
Reading all three is not expected. Come anyway.
single-cell
foundation-models
benchmarking
machine-learning
No matching items