Bayesian and Signal Detection Models

  • McCarley J
  • Benjamin A
  • 25

    Readers

    Mendeley users who have this article in their library.
  • N/A

    Citations

    Citations of this article.

Abstract

(from the chapter) Cognitive systems, whether human or engineered, must often reason from and act on probabilistic information, and many of their decisions are therefore inescapably uncertain. Such probabilistic decision making is the purview of the two approaches reviewed in this chapter: Bayesian analysis and the theory of signal detection (TSD). Bayes' theorem provides a normative means of updating probabilistic beliefs In light of new data, and modern Bayesian techniques allow decision makers to model joint distributions of large sets of variables. For cases in which a human decision maker must make unaided Bayesian inferences, cognitive psychology has developed and validated simple guidelines for data representation to optimize performance. TSD models the transformation of probabilistic assessments into discrete diagnoses, dissociating the representation of evidence from the decision rules applied to that evidence and establishing normative criteria against which the performance of a cognitive system can be measured. Together, Bayesian and signal detection models offer methods of making, modeling, and assessing judgment and decision making under uncertainty, for both human and engineered agents. (PsycINFO Database Record (c) 2014 APA, all rights reserved)

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Authors

  • Jason S. McCarley

  • Aaron S. Benjamin

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free