Research map / Learning theory and algorithms / Kernels and regression theory
Multiplicative local linear hazard estimation and best one-sided cross-validation
Maria Luz Gámiz, María Dolores Martínez-Miranda, Jens Perch Nielsen
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use best one-sided CV instead of double one-sided CV | MBC hazard estimator · Simulated Models 1-5 with left truncation | Rerr vs CV: MBC-DO 0.15 -> MBC-BO 3.66 (Model 2, n=1000) | Improved |
| use best one-sided CV instead of double one-sided CV | MBC hazard estimator · Model 5, no truncation, n=100000 | Rerr vs CV: MBC-DO 4.16 vs MBC-BO 2.28 | Hurt |
| use best one-sided CV instead of double one-sided CV | local linear hazard estimator · Simulated models | Rerr vs CV: LL-DO 1.68 vs LL-BO 1.73 (Model 5, n=10^5) | No clear effect |
| use best one-sided CV instead of double one-sided CV | local linear hazard estimator · Model 5, no truncation, n=50000 | Rerr vs CV: LL-DO 0.80 -> LL-BO 6.45 | Improved |
| use right one-sided CV bandwidth instead of left one-sided (ablation) | local linear, Model 5 no truncation · n=100000 | empirical MISE x10^6: 1894.00 -> 1.43 | Improved |
| use best one-sided CV instead of DO in outstanding claims | MBC estimator · Motor claims forecast | forecast total: MBC-DO 298.69 vs MBC-BO 312.92 | Mixed |
| use MBC instead of local linear hazard estimator | best one-sided CV · Motor claims forecast | forecast total: LL-BO 298.23 vs MBC-BO 312.92 | Mixed |
Closest papers by meaning
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.82)
- Risk and cross validation in ridge regression with correlated samples (ICML 2025 · similarity 0.82)
- K$^2$IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes (ICML 2025 · similarity 0.81)
- Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance? (NeurIPS 2024 · similarity 0.80)
- Concentration and excess risk bounds for imbalanced classification with synthetic oversampling (NeurIPS 2025 · similarity 0.80)
- Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters (ICML 2024 · similarity 0.80)
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.
