Affine invariant divergences associated with proper composite scoring rules and their applications

DOI10.3150/13-BEJ557zbMATH Open1457.62093arXiv1305.2473OpenAlexW2051670307MaRDI QIDQ470075FDOQ470075

Authors: Hironori Fujisawa, Takafumi Kanamori 

Publication date: 11 November 2014

Published in: Bernoulli (Search for Journal in Brave)

Abstract: In statistical analysis, measuring a score of predictive performance is an important task. In many scientific fields, appropriate scores were tailored to tackle the problems at hand. A proper score is a popular tool to obtain statistically consistent forecasts. Furthermore, a mathematical characterization of the proper score was studied. As a result, it was revealed that the proper score corresponds to a Bregman divergence, which is an extension of the squared distance over the set of probability distributions. In the present paper, we introduce composite scores as an extension of the typical scores in order to obtain a wider class of probabilistic forecasting. Then, we propose a class of composite scores, named Holder scores, that induce equivariant estimators. The equivariant estimators have a favorable property, implying that the estimator is transformed in a consistent way, when the data is transformed. In particular, we deal with the affine transformation of the data. By using the equivariant estimators under the affine transformation, one can obtain estimators that do no essentially depend on the choice of the system of units in the measurement. Conversely, we prove that the Holder score is characterized by the invariance property under the affine transformations. Furthermore, we investigate statistical properties of the estimators using Holder scores for the statistical problems including estimation of regression functions and robust parameter estimation, and illustrate the usefulness of the newly introduced scores for statistical forecasting.

Full work available at URL: https://arxiv.org/abs/1305.2473

Recommendations

• Proper scoring rules and Bregman divergence
• Extensive scoring rules
• Minimum scoring rule inference
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Asymptotic minimum scoring rule prediction

zbMATH Keywords

affine invariancedivergenceregression functionBregman scorecomposite scoring rulerobust parameter estimationHölder score

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) General nonlinear regression (62J02) Inference from stochastic processes and prediction (62M20) Robustness and adaptive procedures (parametric inference) (62F35)

Cites Work

• Asymptotic Statistics
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Elements of Information Theory
• Robust Estimation of a Location Parameter
• Title not available (Why is that?)
• Robust Statistics
• Clustering with Bregman divergences.
• Title not available (Why is that?)
• Statistical decision theory and Bayesian analysis. 2nd ed
• Possible generalization of Boltzmann-Gibbs statistics.
• Techniques of variational analysis
• Functional analysis and infinite-dimensional geometry
• A comparison of related density-based minimum divergence estimators
• Robust and efficient estimation by minimising a density power divergence
• Statistical Inference
• Robust parameter estimation with a small bias against heavy contamination
• Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
• Proper local scoring rules
• Proper local scoring rules on discrete sample spaces
• Local proper scoring rules of order two
• Proper Scores for Probability Forecasters
• Projective power entropy and maximum Tsallis entropy distributions
• Information Geometry of U-Boost and Bregman Divergence
• Logistic regression, AdaBoost and Bregman distances
• Families of alpha-, beta- and gamma-divergences: flexible and robust measures of similarities
• The geometry of proper scoring rules
• Title not available (Why is that?)

Cited In (8)

• Statistical inference based on bridge divergences
• Robust estimation of a location parameter with the integrated Hogg function
• Robust sparse Gaussian graphical modeling
• Proper scoring rules and Bregman divergence
• Active learning by query by committee with robust divergences
• A new integrated discrimination improvement index via odds
• Title not available (Why is that?)
• Graph-based composite local Bregman divergences on discrete sample spaces

Uses Software

• robustbase

This page was built for publication: Affine invariant divergences associated with proper composite scoring rules and their applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q470075)