When can you ignore informative censoring?
A simulation study on when adjusting for informative censoring changes your estimate, and when it may not be worth the trade.
A practical question in time-to-event analysis.
Informative censoring is common in pharmacoepidemiology, and inverse probability of censoring weighting (IPCW) is the usual correction, though it comes with a variance cost. When the correction is worth making is not always obvious.
This podium presentation uses simulation to look at how the censoring rate relates to whether adjustment meaningfully changes the estimate. It is a methods talk for anyone making design and analysis choices in time-to-event real-world studies.
Simulation study of informative censoring and IPCW
Focus: when adjustment changes the estimate
For RWE methods and biostatistics teams
Citation
Rathnayaka N, Brookhart A, Hurwitz K. When can we ignore informative censoring? Podium 2A-02, 42nd ISPE Annual Meeting; August 29–September 2, 2026; Milan, Italy.
Schedule a meeting
Share your focus and a preferred day or time in the comments, and we will confirm a slot.