Predictive stochastic complexity and model estimation for finite-state processes

DOI10.1016/0378-3758(94)90092-2zbMath0804.62008OpenAlexW2007451064MaRDI QIDQ1330228

Meir Feder, Marcelo J. Weinberger

Publication date: 12 July 1994

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0378-3758(94)90092-2

zbMATH Keywords

minimum description lengthstrong consistencyfinite-state modelsasymptotic equivalencemodel estimationsequential decision problemsnonpredictive stochastic complexitiespredictiveuniversal processuniversal, sequential, noiseless coding scheme

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Foundations and philosophical topics in statistics (62A01) Statistical aspects of information-theoretic topics (62B10) Source coding (94A29)

Related Items (1)

Variable length Markov chains

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A universal prior for integers and estimation by minimum description length
• Stochastic complexity and modeling
• Estimating the dimension of a model
• Universal coding, information, prediction, and estimation
• Complexity of strings in the class of Markov sources
• Conditional limit theorems under Markov conditioning
• The performance of universal encoding
• Minimax noiseless universal coding for Markov sources
• Estimating the number of states of a finite-state source
• A sequential algorithm for the universal coding of finite memory sources
• Universal prediction of individual sequences
• On the estimation of the order of a Markov chain and universal data compression
• A formal theory of inductive inference. Part II
• TESTS OF FIT IN TIME SERIES
• On the Identifiability Problem for Functions of Finite Markov Chains
• A new look at the statistical model identification

This page was built for publication: Predictive stochastic complexity and model estimation for finite-state processes