Osband's Principle for Identification Functions

DOI10.1007/S00362-023-01428-XOpenAlexW4353060006MaRDI QIDQ6407992FDOQ6407992

Authors Timo Dimitriadis, Tobias Fissler, Johanna F. Ziegel 

Publication date 16 August 2022

Full work available at URL https://doi.org/10.1007/s00362-023-01428-x

Mathematics Subject Classification ID

Point estimation (62F10) Diagnostics, and linear inference and regression (62J20) Complete class results in statistical decision theory (62C07)

Abstract: Given a statistical functional of interest such as the mean or median, a (strict) identification function is zero in expectation at (and only at) the true functional value. Identification functions are key objects in forecast validation, statistical estimation and dynamic modelling. For a possibly vector-valued functional of interest, we fully characterise the class of (strict) identification functions subject to mild regularity conditions.

Recommendations

• Higher order elicitability and Osband's principle
• An identity for the expectation of joint functions of order statistics
• Elicitability and identifiability of set-valued measures of systemic risk
• Order-sensitivity and equivariance of scoring functions
• On the recoverability of forecasters' preferences

Cited In (1)

• Estimation and backtesting of risk measures with emphasis on distortion risk measures

This page was built for publication: Osband's Principle for Identification Functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6407992)