EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Doubly robust and efficient calibration of prediction sets for right-censored time-to-event outcomes

Rebecca Farina, Eric Tchetgen Tchetgen, Arun Kumar Kuchibhotla

Biometrika · 06.07.2026 · 113 (3)

DOI: 10.1093/biomet/asag036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrika, online erschienen am 11.06.2026. Verfasst von Rebecca Farina und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Data Science, Carnegie Mellon University,5000 Forbes Avenue, Pittsburgh, Pennsylvania 15213, U.S.A. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIA NIH HHS, NSF, NIH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Our objective is to construct well-calibrated prediction sets for a time-to-event outcome subject to right censoring with guaranteed coverage. Inspired by modern conformal inference, our approach avoids the need for a well-specified parametric or semiparametric survival model. Unlike existing conformal methods for survival data, which assume Type-I censoring with fully observed censoring times, we consider the more common right-censoring setting in which only the censoring time or the event time is observed, whichever comes first. Under a standard conditional independence censoring condition, we propose and analyse several lower prediction bounds for the survival time of a future observation, including inverse-probability-of-censoring weighting and its augmented version based on the semiparametric efficient influence function for the relevant marginal quantile of the outcome, accounting for dependent censoring. We formally establish asymptotic coverage guarantees for the proposed methods and demonstrate, both theoretically and through empirical experiments, that the augmented approach substantially improves efficiency over all other proposed methods. Specifically, its coverage error bound is doubly robust, and therefore of second order, thus ensuring that it is asymptotically negligible relative to the coverage error of the other methods.

Schlagwörter

Stichwörter der Autor:innen

Censored dataConformal predictionDouble robustnessInverse-probability-of-censoring weightingPrediction setSemiparametric efficiency theoryTime-to-event outcome

Autor:innen und Institutionen

  • Department of Statistics and Data Science, Carnegie Mellon University,5000 Forbes Avenue, Pittsburgh, Pennsylvania 15213, U.S.A.
  • Department of Statistics and Data Science, The Wharton School, University of Pennsylvania, 265 South 37th Street, Philadelphia, Pennsylvania 19104, U.S.A. ett@wharton.upenn.edu.
  • Department of Statistics and Data Science, Carnegie Mellon University,5000 Forbes Avenue, Pittsburgh, Pennsylvania 15213, U.S.A. arunku@stat.cmu.edu.

Förderung

  • NIA NIH HHS
  • NSF
  • NIH

Zitieren

APA

Farina, R., Tchetgen Tchetgen, E., & Kuchibhotla, A. K. (2026). Doubly robust and efficient calibration of prediction sets for right-censored time-to-event outcomes. Biometrika, 113(3). https://doi.org/10.1093/biomet/asag036

Vancouver

Farina R, Tchetgen Tchetgen E, Kuchibhotla AK. Doubly robust and efficient calibration of prediction sets for right-censored time-to-event outcomes. Biometrika. 2026;113(3). doi:10.1093/biomet/asag036

BibTeX
@article{Farina2026,
  author = {Farina, Rebecca and Tchetgen Tchetgen, Eric and Kuchibhotla, Arun Kumar},
  title = {Doubly robust and efficient calibration of prediction sets for right-censored time-to-event outcomes},
  journal = {Biometrika},
  year = {2026},
  volume = {113},
  number = {3},
  doi = {10.1093/biomet/asag036}
}
Kostenlos starten →