Document Detail


Asymptotic theory of information-theoretic experimental design.
MedLine Citation:
PMID:  15901405     Owner:  NLM     Status:  PubMed-not-MEDLINE    
Abstract/OtherAbstract:
We discuss an idea for collecting data in a relatively efficient manner. Our point of view is Bayesian and information-theoretic: on any given trial, we want to adaptively choose the input in such a way that the mutual information between the (unknown) state of the system and the (stochastic) output is maximal, given any prior information (including data collected on any previous trials). We prove a theorem that quantifies the effectiveness of this strategy and give a few illustrative examples comparing the performance of this adaptive technique to that of the more usual nonadaptive experimental design. In particular, we calculate the asymptotic efficiency of the information-maximization strategy and demonstrate that this method is in a well-defined sense never less efficient--and is generically more efficient--than the nonadaptive strategy. For example, we are able to explicitly calculate the asymptotic relative efficiency of the staircase method widely employed in psychophysics research and to demonstrate the dependence of this efficiency on the form of the psychometric function underlying the output responses.
Authors:
Liam Paninski
Related Documents :
20423925 - A general inefficacy interim monitoring rule for randomized clinical trials.
2721815 - The use of a hand-held computer to record clinical trial data in general practice: a pi...
12689735 - Estimating the distribution of nonterminal event time in the presence of mortality or i...
17240655 - A cautionary note on design implications when the primary analysis is a stratified anal...
1335175 - The evolution of toxic effluents in fires and the assessment of toxic hazard.
12775065 - Selective remediation of contaminated sites using a two-level multiphase strategy and g...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Neural computation     Volume:  17     ISSN:  0899-7667     ISO Abbreviation:  Neural Comput     Publication Date:  2005 Jul 
Date Detail:
Created Date:  2005-05-19     Completed Date:  2005-07-15     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9426182     Medline TA:  Neural Comput     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1480-507     Citation Subset:  -    
Affiliation:
Gatsby Computational Neuroscience Unit, University College London, London, WC1N 3AR, UK. liam@gatsby.ucl.ac.uk
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Theory of the snowflake plot and its relations to higher-order analysis methods.
Next Document:  Maximum likelihood set for estimating a probability mass function.