1973 InformationTheoryAndAnExtOfMLE

Jump to: navigation, search

Subject Headings: IID Random Variable Set, Maximum Likelihood Estimation Algorithm.


  • Keywords: asymptotic methods; curve fitting; information theory; maximum likelihood estimates; statistical decision theory; mathematical models; optimization; probability distribution functions; regression analysis; signal processing


  • In this paper it is shown that the classical maximum likelihood principle can be considered to be a method of asymptotic realization of an optimum estimate with respect to a very general information theoretic criterion. This observation allows an extension of the principle to provide answers to many practical problems of statistical model fitting.

5. Applications

5.5 Autoregressive Modeling Fittein in Time Series

  • Though the discussion in the present paper has been limited to the realization of independent and identically distributed random variables, by following the approach of Billingsley ...,

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
1973 InformationTheoryAndAnExtOfMLEHirotugu AkaikeInformation Theory and an Extension of the Maximum Likelihood PrincipleProceedings of the Second International Symposium on Information Theoryhttp://books.google.com/books?id=QN4Dn20r9uoC&pg=PA1991973