Rissanen, Jorma J. Fisher information and stochastic complexity. (English) Zbl 0856.94006 IEEE Trans. Inf. Theory 42, No. 1, 40-47 (1996). Author’s abstract: By taking into account the Fisher information and removing an inherent redundancy in earlier two-part codes, a sharper code length as the stochastic complexity and the associated universal process are derived for a class of parametric processes. The main condition required is that the maximum-likelihood estimates satisfy the Central Limit Theorem. The same code length is also obtained from the so-called maximum-likelihood code. Reviewer: P.N.Rathie (Brasilia) Cited in 2 ReviewsCited in 97 Documents MSC: 94A17 Measures of information, entropy 62M99 Inference from stochastic processes Keywords:central limit theorem; Fisher information; code length; stochastic complexity; parametric processes; maximum-likelihood estimates; maximum-likelihood code PDFBibTeX XMLCite \textit{J. J. Rissanen}, IEEE Trans. Inf. Theory 42, No. 1, 40--47 (1996; Zbl 0856.94006) Full Text: DOI