Proper Scoring Rules for Survival Analysis

Hiroki Yanagisawa
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39165-39182, 2023.

Abstract

Survival analysis is the problem of estimating probability distributions for future event times, which can be seen as a problem in uncertainty quantification. Although there are fundamental theories on strictly proper scoring rules for uncertainty quantification, little is known about those for survival analysis. In this paper, we investigate extensions of four major strictly proper scoring rules for survival analysis and we prove that these extensions are proper under certain conditions, which arise from the discretization of the estimation of probability distributions. We also compare the estimation performances of these extended scoring rules by using real datasets, and the extensions of the logarithmic score and the Brier score performed the best.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-yanagisawa23a, title = {Proper Scoring Rules for Survival Analysis}, author = {Yanagisawa, Hiroki}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {39165--39182}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/yanagisawa23a/yanagisawa23a.pdf}, url = {https://proceedings.mlr.press/v202/yanagisawa23a.html}, abstract = {Survival analysis is the problem of estimating probability distributions for future event times, which can be seen as a problem in uncertainty quantification. Although there are fundamental theories on strictly proper scoring rules for uncertainty quantification, little is known about those for survival analysis. In this paper, we investigate extensions of four major strictly proper scoring rules for survival analysis and we prove that these extensions are proper under certain conditions, which arise from the discretization of the estimation of probability distributions. We also compare the estimation performances of these extended scoring rules by using real datasets, and the extensions of the logarithmic score and the Brier score performed the best.} }
Endnote
%0 Conference Paper %T Proper Scoring Rules for Survival Analysis %A Hiroki Yanagisawa %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-yanagisawa23a %I PMLR %P 39165--39182 %U https://proceedings.mlr.press/v202/yanagisawa23a.html %V 202 %X Survival analysis is the problem of estimating probability distributions for future event times, which can be seen as a problem in uncertainty quantification. Although there are fundamental theories on strictly proper scoring rules for uncertainty quantification, little is known about those for survival analysis. In this paper, we investigate extensions of four major strictly proper scoring rules for survival analysis and we prove that these extensions are proper under certain conditions, which arise from the discretization of the estimation of probability distributions. We also compare the estimation performances of these extended scoring rules by using real datasets, and the extensions of the logarithmic score and the Brier score performed the best.
APA
Yanagisawa, H.. (2023). Proper Scoring Rules for Survival Analysis. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:39165-39182 Available from https://proceedings.mlr.press/v202/yanagisawa23a.html.

Related Material