Likelihood-Free Methods for Cognitive Science
Buch in deiner Nähe kaufen
Beschreibung
This book explains the foundation of approximate Bayesian computation (ABC), an approach to Bayesian inference that does not require the specification of a likelihood function. As a result, ABC can be used to estimate posterior distributions of parameters for simulation-based models. Simulation-based models are now very popular in cognitive science, as are Bayesian methods for performing parameter inference. As such, the recent developments of likelihood-free techniques are an important advancement for the field.
Chapters discuss the philosophy of Bayesian inference as well as provide several algorithms for performing ABC. Chapters also apply some of the algorithms in a tutorial fashion, with one specific application to the Minerva 2 model. In addition, the book discusses several applications of ABC methodology to recent problems in cognitive science.
Likelihood-Free Methods for Cognitive Science will be of interest to researchers and graduate students working in experimental, applied, and cognitive science.
Provides an in-depth foundation of approximate Bayesian analysis (ABC) Offers a tutorial demonstration of a popular model in cognitive science that can be readily adapted to other models Reviews many of the most prominent algorithms for performing likelihood-free Bayesian analysis
Autor*in
James J. Palestro
Themen in »Likelihood-Free Methods for Cognitive Science«
Likelihood-free Bayesian analysis Approximate Bayesian computation Minerva 2 Tutorial Model Estimation Probability Density Approximation ABCDE Gibbs ABC Cognitive Psychology Modeling Bayesian methods