Osband's Principle for Identification Functions
Statistics Theory
2023-03-24 v1 Statistics Theory
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.
Keywords
Cite
@article{arxiv.2208.07685,
title = {Osband's Principle for Identification Functions},
author = {Timo Dimitriadis and Tobias Fissler and Johanna Ziegel},
journal= {arXiv preprint arXiv:2208.07685},
year = {2023}
}