Search results for "Scoring rule"

showing 9 items of 9 documents

Extropy: Complementary Dual of Entropy

2015

This article provides a completion to theories of information based on entropy, resolving a longstanding question in its axiomatization as proposed by Shannon and pursued by Jaynes. We show that Shannon's entropy function has a complementary dual function which we call "extropy." The entropy and the extropy of a binary distribution are identical. However, the measure bifurcates into a pair of distinct measures for any quantity that is not merely an event indicator. As with entropy, the maximum extropy distribution is also the uniform distribution, and both measures are invariant with respect to permutations of their mass functions. However, they behave quite differently in their assessments…

Bregman divergenceFOS: Computer and information sciencesStatistics and ProbabilitySettore MAT/06 - Probabilita' E Statistica MatematicaKullback–Leibler divergenceComputer Science - Information TheoryGeneral MathematicsFOS: Physical sciencesBinary numberMathematics - Statistics TheoryStatistics Theory (math.ST)Kullback–Leibler divergenceBregman divergenceproper scoring rulesGini index of heterogeneityDifferential entropyBinary entropy functionFOS: MathematicsEntropy (information theory)Statistical physicsDual functionAxiomMathematicsdifferential and relative entropy/extropy Kullback- Leibler divergence Bregman divergence duality proper scoring rules Gini index of heterogeneity repeat rate.Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniDifferential and relative entropy/extropyInformation Theory (cs.IT)Probability (math.PR)repeat ratePhysics - Data Analysis Statistics and ProbabilitydualityStatistics Probability and UncertaintySettore SECS-S/01 - StatisticaMathematics - ProbabilityData Analysis Statistics and Probability (physics.data-an)Statistical Science
researchProduct

Approximations in Statistics from a Decision-Theoretical Viewpoint

1987

The approximation of the probability density p(.) of a random vector x∊X by another (possibly more convenient) probability density q(.) which belongs to a certain class Q is analyzed as a decision problem where the action space is the class Qof available approximations, the relevant uncertain event is the actual value of the vector x and the utility function is a proper scoring rule. The logarithmic divergence is shown to play a rather special role within this approach. The argument lies entirely within a Bayesian framework.

Class (set theory)Multivariate random variableScoring ruleStatisticsProbability density functionFunction (mathematics)Decision problemDivergence (statistics)MathematicsEvent (probability theory)
researchProduct

Assessing fat-tailed sequential forecast distributions for the Dow-Jones index with logarithmic scoring rules

2007

We use the logarithmic scoring rule for distributions to assess a variety of fat-tailed sequential forecasting distributions for the Dow-Jones industrial stock index from 1980 to the present. The methodology applies Bruno de Finetti''s contributions to understanding how to compare the quality of different coherent forecasting distributions for the same sequence of observations, using proper scoring rules. Four different forms of forecasting distributions are compared: a mixture Normal, a mixture of convex combinations of three Normal distributions, a mixture exponential power distribution, and a mixture of a convex combination of three exponential power distributions. The mixture linear com…

Dow-Jones index exponential power distributions fat tails logarithmic scoring rule mixture distributions partial exchangeability proper scoring rules subjective probability subjectivist statistical methods.
researchProduct

The Duality of Entropy/Extropy, and Completion of the Kullback Information Complex

2018

The refinement axiom for entropy has been provocative in providing foundations of information theory, recognised as thoughtworthy in the writings of both Shannon and Jaynes. A resolution to their concerns has been provided recently by the discovery that the entropy measure of a probability distribution has a dual measure, a complementary companion designated as &ldquo

Kullback–Leibler divergenceSettore MAT/06 - Probabilita' E Statistica MatematicaLogarithmGeneral Physics and Astronomylcsh:Astrophysics02 engineering and technologyBregman divergenceMathematical proofInformation theory01 natural sciencesArticle010104 statistics & probabilityFermi–Dirac entropyKullback symmetric divergencelcsh:QB460-4660202 electrical engineering electronic engineering information engineeringEntropy (information theory)0101 mathematicslcsh:Sciencerelative entropy/extropyAxiomMathematics020206 networking & telecommunicationslcsh:QC1-999total logarithmic scoring ruleProbability distributiondualityPareto optimal exchangelcsh:QprevisionextropySettore SECS-S/01 - StatisticaentropyMathematical economicslcsh:PhysicsEntropy
researchProduct

Sequentially Forecasting Economic Indices Using Mixture Linear Combinations of EP Distributions

2021

This article displays an application of the statistical method moti- vated by Bruno de Finetti's operational subjective theory of probability. We use exchangeable forecasting distributions based on mixtures of linear com- binations of exponential power (EP) distributions to forecast the sequence of daily rates of return from the Dow-Jones index of stock prices over a 20 year period. The operational subjective statistical method for comparing distributions is quite different from that commonly used in data analysis, because it rejects the basic tenets underlying the practice of hypothesis test- ing. In its place, proper scoring rules for forecast distributions are used to assess the values o…

Settore MAT/06 - Probabilita' E Statistica MatematicaLogarithmDow-Jones index exponential power distributions fat tails logarithmic scoring rule mixture distributions partial exchangeability proper scoring rules subjective probability subjectivist statistical methods.Scoring ruleStatistical parameterExponential functionNormal distributionSettore SECS-S/06 -Metodi Mat. dell'Economia e d. Scienze Attuariali e Finanz.StatisticsEconometricsSettore SECS-S/01 - StatisticaLinear combinationMathematicsStatistical hypothesis testingJournal of Data Science
researchProduct

Completing the logarithmic scoring rule for assessing probability distributions

2012

We propose and motivate an expanded version of the logarithmic score for forecasting distributions, termed the Total Log score. It incorporates the usual logarithmic score, which is recognised as incomplete and has been mistakenly associated with the likelihood principle. The expectation of the Total Log score equals the Negentropy plus the Negextropy of the distribution. We examine both discrete and continuous forms of the scoring rule, and we discuss issues of scaling for scoring assessments. The analysis suggests the dual tracking of the quadratic score along with the usual log score when assessing the qualities of probability distributions. An application to the sequential scoring of f…

Settore MAT/06 - Probabilita' E Statistica MatematicaLogarithmScoring ruleDow-Jones stock indexScoreLikelihood principletotal log scorelogarithmic scoreProbability theoryStatisticsproper scoring ruleEconometricsEntropy (information theory)Probability distributionNegentropyextropyentropySettore SECS-S/01 - StatisticaMathematicsAIP Conference Proceedings
researchProduct

SCORING ALTERNATIVE FORECAST DISTRIBUTIONS: COMPLETING THE KULLBACK DISTANCE COMPLEX

2018

We develop two surprising new results regarding the use of proper scoring rules for evaluating the predictive quality of two alternative sequential forecast distributions. Both of the proponents prefer to be awarded a score derived from the other's distribution rather than a score awarded on the basis of their own. A Pareto optimal exchange of their scoring outcomes provides the basis for a comparison of forecast quality that is preferred by both forecasters, and also evades a feature of arbitrariness inherent in using the forecasters' own achieved scores. The well-known Kullback divergence, used as a measure of information, is evaluated via the entropies in the two forecast distributions a…

Settore MAT/06 - Probabilita' E Statistica MatematicaProbability (math.PR)Mathematics - Statistics TheoryStatistics Theory (math.ST)PARETO OPTIMAL EXCHANGETOTAL LOGARITHMIC SCORING RULEKULLBACK SYMMETRIC DIVERGENCEPREVISIONENTROPY/EXTROPYSettore SECS-S/06 -Metodi Mat. dell'Economia e d. Scienze Attuariali e Finanz.FOS: MathematicsMathematics - ProbabilityCROSS ENTROPYBREGMAN DIVERGENCE
researchProduct

Coherent Conditional Previsions and Proper Scoring Rules

2012

In this paper we study the relationship between the notion of coherence for conditional prevision assessments on a family of finite conditional random quantities and the notion of admissibility with respect to bounded strictly proper scoring rules. Our work extends recent results given by the last two authors of this paper on the equivalence between coherence and admissibility for conditional probability assessments. In order to prove that admissibility implies coherence a key role is played by the notion of Bregman divergence.

Settore MAT/06 - Probabilita' E Statistica Matematicabregman divergenceproper scor- ing rulesConditional prevision assessmentsconditional scoring rulesstrong dominanceConditional probabilityweak dominanceCoherence (statistics)Bregman divergenceConditional prevision assessments coherence proper scoring rules conditional scoring rules weak dominance strong dominance admissibility Bregman divergence.proper scoring rulescoherenceBounded functionKey (cryptography)admissibilityConditional prevision assessments; conditional scoring rules; admissibility; proper scor- ing rules; weak dominance; strong dominanceEquivalence (measure theory)Mathematical economicsconditional prevision assessments; strong dominance; admissibility; proper scoring rules; bregman divergence; weak dominance; conditional scoring rules; coherenceMathematics
researchProduct

Coherent conditional probabilities and proper scoring rules

2011

In this paper we study the relationship between the notion of coherence for conditional probability assessments on a family of conditional events and the notion of admissibility with respect to scoring rules. By extending a recent result given in literature for unconditional events, we prove, for any given strictly proper scoring rule s, the equivalence between the coherence of a conditional probability assessment and its admissibility with respect to s. In this paper we focus our analysis on the case of continuous bounded scoring rules. In this context a key role is also played by Bregman divergence and by a related theoretical aspect. Finally, we briefly illustrate a possible way of defin…

total coherenceSettore MAT/06 - Probabilita' E Statistica Matematicabregman divergencestrong dominanceconditional scoring rulesConditional probability assessments coherence penalty criterion proper scoring rules conditional scoring rules weak dominance strong dominance admissibility Bregman divergence g-coherence total coherence imprecise probability assessments.weak dominancestrong dominance; conditional probability assessments; imprecise probability assessments; gcoherence; proper scoring rules; bregman divergence; weak dominance; coherence; imprecise probability assessments.; admissibility; g-coherence; penalty criterion; conditional scoring rules; total coherencepenalty criteriongcoherenceproper scoring rulescoherenceconditional probability assessmentsg-coherenceimprecise probability assessmentsadmissibility
researchProduct