Approximating a sequence of observations by a simple process

DOI10.1214/009053604000000643MaRDI QIDQ2388342zbMATH OpenOpenAlexFDO

Authors Dinah Rosenberg, Eilon Solan, Nicolas Vieille

Publication date 12 September 2005

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

Full work available at URL https://arxiv.org/abs/math/0508607

zbMATH Keywords

data approximationhidden Markus chainsnonhomogeneous Markov chains

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Continuous-time Markov processes on discrete state spaces (60J27) Markov processes (60J99) Non-Markovian processes: estimation (62M09)

Abstract: Given an arbitrary long but finite sequence of observations from a finite set, we construct a simple process that approximates the sequence, in the sense that with high probability the empirical frequency, as well as the empirical one-step transitions along a realization from the approximating process, are close to that of the given sequence. We generalize the result to the case where the one-step transitions are required to be in given polyhedra.

Recommendations

• Approximating Markov chains.
• Approximation by mutually completely dependent processes
• Empirical Distributions of Beliefs Under Imperfect Observation
• On finding predictors for arbitrary families of processes
• scientific article; zbMATH DE number 3854140

Cites work

• An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology
• Approximating the Permanent
• Faster mixing via average conductance
• Hoeffding's inequality for uniformly ergodic Markov chains
• scientific article; zbMATH DE number 3249395 (Why is no real title available?)
• Perturbed Markov chains
• Statistical Inference for Probabilistic Functions of Finite State Markov Chains
• The probabilistic method. With an appendix on the life and work of Paul Erdős.

Cited in

(2)

• Acceptable strategy profiles in stochastic games
• Empirical Distributions of Beliefs Under Imperfect Observation

This page was built for publication: Approximating a sequence of observations by a simple process

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2388342)