Partially identifying competing risks models: An application to the war on cancer

A-Tier
Journal: Journal of Econometrics
Year: 2023
Volume: 234
Issue: 2
Pages: 536-564

Score contribution per author:

4.022 = (α=2.01 / 1 authors) × 2.0x A-tier

α: calibrated so average coauthorship-adjusted count equals average raw count

Abstract

Competing risks models for discretely measured durations are partially identifying due to the unknown dependence structure between risks and the discrete nature of the outcome. This article develops a highly tractable bounds approach for underlying distributions of latent durations by exploiting the discreteness. Bounds are obtained from a system of nonlinear (in)equalities. I devise a sequential solution method that requires much less computational burden than existing methods. Asymptotic properties of bound estimators and a simple bootstrap procedure are provided. I apply the proposed approach to re-evaluate trends in cancer mortality extending the data studied in Honoré and Lleras-Muney (2006). Estimated patterns differ from the original findings.

Technical Details

RePEc Handle
repec:eee:econom:v:234:y:2023:i:2:p:536-564
Journal Field
Econometrics
Author Count
1
Added to Database
2026-01-25