Approximate Bayesian computation: Difference between revisions

Revision as of 10:37, 11 January 2013

Revision as of 10:42, 11 January 2013

Line 1:

[[File:Approximate Bayesian computation.tif|thumb|300px|Parameter estimation using approximate Bayesian computation.<ref name="WodakSunnåker2013">{{cite journal|last1=Wodak|first1=Shoshana|last2=Sunnåker|first2=Mikael|last3=Busetto|first3=Alberto Giovanni|last4=Numminen|first4=Elina|last5=Corander|first5=Jukka|last6=Foll|first6=Matthieu|last7=Dessimoz|first7=Christophe|title=Approximate Bayesian Computation|journal=PLoS Computational Biology|volume=9|issue=1|year=2013|pages=e1002803|issn=1553-7358|doi=10.1371/journal.pcbi.1002803}}</ref>]]

'''Approximate Bayesian computation (ABC)''' is a family of computational techniques in [[Bayesian statistics]]. These simulation techniques operate on summary data (such as population mean, or variance) to make broad inferences with less computation than might be required if all available data were analyzed in detail. They are especially useful in situations where evaluation of the likelihood is computationally prohibitive, or whenever suitable likelihoods are not available.