论文信息 - Bayesian information in an experiment and the Fisher information distance - 字舞流文

Bayesian information in an experiment and the Fisher information distance

There are two forms of Fisher information; for the parameter of a model and for the information in a density model. These two forms are shown to be fundamentally connected through a measure of gain in information from a Bayesian experiment.

Stephen G. Walker | S. Walker

[1] David M. Steinberg,et al. Fast Computation of Designs Robust to Parameter Uncertainty for Nonlinear Settings , 2009, Technometrics.

[2] T. Papaioannou,et al. On Two Forms of Fisher's Measure of Information , 2005 .

[3] D. Lindley. On a Measure of the Information Provided by an Experiment , 1956 .

[4] C. E. SHANNON,et al. A mathematical theory of communication , 1948, MOCO.

[5] Cyril Roberto,et al. Bounds on the deficit in the logarithmic Sobolev inequality , 2014, 1408.2115.

[6] A. Barron,et al. Fisher information inequalities and the central limit theorem , 2001, math/0111020.

[7] R. Gill,et al. Applications of the van Trees inequality : a Bayesian Cramr-Rao bound , 1995 .

[8] Anthony N. Pettitt,et al. Fully Bayesian Experimental Design for Pharmacokinetic Studies , 2015, Entropy.

[9] T. Apostol. Mathematical Analysis , 1957 .

[10] E. L. Lehmann,et al. Theory of point estimation , 1950 .

[11] Pseudo-Bayesian A-optimal designs for estimating the point of maximum in component-amount Darroch–Waller mixture model , 2012 .