Always Good Turing: asymptotically optimal probability estimation

DOI10.1126/SCIENCE.1088284MaRDI QIDQ3101376zbMATH OpenOpenAlexWikidataFDO

Authors Alon Orlitsky, Narayana P. Santhanam, Junan Zhang

Publication date 28 November 2011

Published in Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1126/science.1088284

Mathematics Subject Classification ID

History of mathematics in the 20th century (01A60) History of statistics (62-03) Asymptotic distribution theory in statistics (62E20) History of information and communication theory (94-03) Cryptography (94A60)

Recommendations

• On Turing's formula for word probabilities
• Asymptotic properties of Turing's formula in relative error
• Entropy estimation in Turing's perspective
• Statistical implications of Turing's formula
• On consistent and rate optimal estimation of the missing mass

Cited in

(29)

• A lower bound on compression of unknown alphabets
• Emergence of random selections in evolution of biological populations
• On consistent and rate optimal estimation of the missing mass
• A Good-Turing estimator for feature allocation models
• A new estimator for the number of species in a population
• Methods for diversity and overlap analysis in T-cell receptor populations
• Probabilistic logic with minimum perplexity: Application to language modeling
• Optimal estimator of hypothesis probability for data mining problems with small samples
• Statistical implications of Turing's formula
• Impact of model choice on LR assessment in case of rare haplotype match (frequentist approach)
• Maximum Likelihood Set for Estimating a Probability Mass Function
• Concentration bounds for unigram language models
• Convergence properties in certain occupancy problems including the Karlin-Rouault law
• Quadratic Tsallis entropy bias and generalized maximum entropy models
• Moderate deviations for a nonparametric estimator of sample coverage
• Turing’s anticipation of empirical bayes in connection with the cryptanalysis of the naval enigma^*
• Learning Theory
• Consistent estimation of small masses in feature sampling
• Measuring what's missing: practical estimates of coverage for stochastic simulations
• Good-Turing frequency estimation in a finite population
• On the performance of Turing's formula: a simulation study
• Encoding through patterns: regression tree-based neuronal population models
• Quantifying Stimulus Discriminability: A Comparison of Information Theory and Ideal Observer Analysis
• Generalized Good-Turing Improves Missing Mass Estimation
• Bayesian approach to LR assessment in case of rare type match
• Good-bootstrap: simultaneous confidence intervals for large alphabet distributions
• Asymptotic properties of Turing's formula in relative error
• Confidence Intervals for Parameters of Unobserved Events
• Bayesian nonparametric inference for ``species-sampling problems

This page was built for publication: Always Good Turing: asymptotically optimal probability estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3101376)