AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Kernelized Stein Discrepancy Tests of Goodness-of-fit for Time-to-Event Data

Tamara Fernandez, Nicolas Rivera, Wenkai Xu, Arthur Gretton

ICML 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the martingale Stein test on periodic-hazard alternatives instead of MMDGoodness-of-fit testing for censored time-to-event data · Periodic hazardpowerImproved
Transform observed times using the null CDF before applying mKSD (ablation)mKSD · Periodic hazardpowerImproved
Transform observed times using the null CDF before applying mKSD (ablation)mKSD · Periodic hazard, θ = 4power: around 75 %Improved
Use pKSD to test goodness of fit rather than hazard proportionalitypKSD · Weibull hazardpowerHurt
Test the proportional-hazard family with pKSD, ignoring rate differences within that familypKSD · Proportional Weibull hazardstype I errorMixed
Add the proportional-hazard-family null rather than testing a single specified hazardpKSD · Proportional hazards with different ratesrejection rateNo clear effect
Use mKSD for Weibull alternatives instead of the other kernel-based testsCensored-data goodness-of-fit tests · Weibull hazardpowerNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy