Two-Stage Plans for Estimating a Threshold Value of a Regression Function

TL;DR

This paper proposes a two-stage nonparametric isotonic regression method to efficiently estimate a threshold in a regression function, outperforming existing methods especially with limited data or complex functions.

Contribution

It introduces a novel two-stage isotonic regression procedure that accelerates convergence and improves estimation accuracy over existing methods.

Findings

Two-stage plans outperform one-stage procedures in convergence rate.

Likelihood Ratio confidence intervals are recommended for robustness.

Simulation and real data demonstrate practical effectiveness.

Abstract

This study investigates two-stage plans based on nonparametric procedures for estimating an inverse regression function at a given point. Specifically, isotonic regression is used at stage one to obtain an initial estimate followed by another round of isotonic regression in the vicinity of this estimate at stage two. It is shown that such two stage plans accelerate the convergence rate of one-stage procedures and are superior to existing two-stage procedures that use local parametric approximations at stage two when the available budget is moderate and/or the regression function is 'ill-behaved'. Both Wald and Likelihood Ratio type confidence intervals for the threshold value of interest are investigated and the latter are recommended in applications due to their simplicity and robustness. The developed plans are illustrated through a comprehensive simulation study and an application to car fuel efficiency data.