Work

Variance-reduced risk inference in semi-supervised settings

Year: 2025

Type: article

Abstract: In the estimating equation framework, this paper develops a variance-reducedestimation procedure when next to a short sequence of interest another longer auxiliary sequenceis available. The proposed method does not require modeling and inferring the dependencebetween the short and long sequences. We apply the proposed method to develop a novelvariance-reduced estimator for three popular risk measures: Value-at-Risk, Expected Shortfall,and Expectile. A simulation study confirms the good performance of our method. Finally,applications to the Danish fire losses and to hurricane losses are presented.

Source: Scandinavian Actuarial Journal

DOI: 10.1080/03461238.2025.2587657

Authors: John H. J. Einmahl, Liang Peng

Institutions: Tilburg University, Georgia State University

Language: English

Topic: Probability and Risk Models

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: PSI