Multiplicative local linear hazard estimation and best one-sided cross-validation

TL;DR

This paper introduces a new class of cross-validation methods for local linear kernel hazard estimation, providing detailed theoretical analysis and demonstrating superior small sample performance and practical effectiveness.

Contribution

It develops the mathematical theory for multiplicative local linear hazard estimation and introduces the best one-sided cross-validation method with improved performance.

Findings

Excellent practical performance of the new cross-validation method

Strong small sample performance demonstrated

Theoretical guarantees established for the new class

Abstract

This paper develops detailed mathematical statistical theory of a new class of cross-validation techniques of local linear kernel hazards and their multiplicative bias corrections. The new class of cross-validation combines principles of local information and recent advances in indirect cross-validation. A few applications of cross-validating multiplicative kernel hazard estimation do exist in the literature. However, detailed mathematical statistical theory and small sample performance are introduced via this paper and further upgraded to our new class of best one-sided cross-validation. Best one-sided cross-validation turns out to have excellent performance in its practical illustrations, in its small sample performance and in its mathematical statistical theoretical performance.