Proper local scoring rules

DOI10.1214/12-AOS971zbMATH Open1246.62011arXiv1101.5011WikidataQ57394012 ScholiaQ57394012MaRDI QIDQ450049FDOQ450049

Authors: Matthew Parry, A. Philip Dawid, Steffen Lauritzen 

Publication date: 3 September 2012

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We investigate proper scoring rules for continuous distributions on the real line. It is known that the log score is the only such rule that depends on the quoted density only through its value at the outcome that materializes. Here we allow further dependence on a finite number $m$ of derivatives of the density at the outcome, and describe a large class of such $m$-local proper scoring rules: these exist for all even $m$ but no odd $m$. We further show that for $mgeq2$ all such $m$-local rules can be computed without knowledge of the normalizing constant of the distribution.

Full work available at URL: https://arxiv.org/abs/1101.5011

Recommendations

• Proper local scoring rules on discrete sample spaces
• The uniqueness of local proper scoring rules: the logarithmic family
• Local proper scoring rules of order two
• Theory and applications of proper scoring rules
• Extensive scoring rules

zbMATH Keywords

entropyscore matchingconcavitydivergenceEuler-Lagrange equationhomogeneityvariational methodsintegration by partsBregman scorelocal function

Mathematics Subject Classification ID

Foundational topics in statistics (62A99) Statistical decision theory (62C99)

Cites Work

• Robust Statistics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Some extensions of score matching
• Expected information as ecpected utility
• Estimation of non-normalized statistical models by score matching
• Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems
• Title not available (Why is that?)
• The calculus of variations
• Proper local scoring rules on discrete sample spaces
• Local proper scoring rules of order two
• Title not available (Why is that?)
• The geometry of proper scoring rules
• Information Divergence Geometry and the Application to Statistical Machine Learning
• Title not available (Why is that?)

Cited In (42)

• Discussion of: ``Identifiability of latent-variable and structural-equation models: from linear to nonlinear
• Affine statistical bundle modeled on a Gaussian Orlicz-Sobolev space
• Holonomic extended least angle regression
• Bayesian model selection based on proper scoring rules
• Extensive scoring rules
• Estimation of spatial processes using local scoring rules: spatial special issue
• Wasserstein Riemannian geometry of Gaussian densities
• Local proper scoring rules of order two
• Proper local scoring rules on discrete sample spaces
• Bootstrap adjustments of signed scoring rule root statistics
• The Hyvärinen scoring rule in Gaussian linear time series models
• Simultaneous inference for pairwise graphical models with generalized score matching
• Scoring rules for statistical models on spheres
• A note on Bayesian model selection for discrete data using proper scoring rules
• Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models
• Generalized score matching for non-negative data
• Bayesian model comparison with the Hyvärinen score: computation and consistency
• Information geometry formalism for the spatially homogeneous Boltzmann equation
• Statistical analysis of distance estimators with density differences and density ratios
• Comparison of stochastic frontier models using the Hyvärinen factor
• Linear scoring rules for probabilistic binary classification
• Unbiased risk estimation and scoring rules
• Minimum scoring rule inference
• Title not available (Why is that?)
• Affine invariant divergences associated with proper composite scoring rules and their applications
• Information geometry of smooth densities on the Gaussian space: Poincaré inequalities
• Ensemble distributional forecasting for insurance loss reserving
• A proper scoring rule for minimum information bivariate copulas
• Theory and applications of proper scoring rules
• Objective Bayesian inference with proper scoring rules
• Title not available (Why is that?)
• Higher-order asymptotics for scoring rules
• Graph-based composite local Bregman divergences on discrete sample spaces
• Title not available (Why is that?)
• On a class of objective priors from scoring rules (with discussion)
• Local scale invariance and robustness of proper scoring rules
• The uniqueness of local proper scoring rules: the logarithmic family
• A copula model for marked point process with a terminal event: an application in dynamic prediction of insurance claims
• Does data splitting improve prediction?
• Measurability of functionals and of ideal point forecasts
• Bayesian experimental design without posterior calculations: an adversarial approach
• A construction principle for proper scoring rules

This page was built for publication: Proper local scoring rules

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q450049)