Marcus Lindqvist · Head of Clinical Data Science · 6 min read
Enrolment forecasts inherit the optimism of the assumptions used to build the study plan, then compound it.
Calibrating against historical realised curves — including the studies nobody likes to cite — is the single highest-value correction available.
We publish forecast intervals rather than points, and score our own past forecasts publicly within the programme. Accountability improves calibration faster than any model change.
- forecasting
- clinical
- statistics