ECON 123A, Fall 2011, Lecture 6Dale J. Poirier6-1(5.1)5Interval EstimationFrom the Bayesian standpoint, given a region ÷d1and the data y, it ismeaningful to ask what is theprobabilitythat 2lies in ÷? The answer isdirect:where "(0 < "< 1) is defined implicitly in (5.1). C÷is known as a 1-"Bayesian credible region. CThere is no need to introduce the additional frequentist concept of“confidence.”
This preview has intentionally blurred sections.
Sign up to view the full version.