Revision as of 12:43, 22 November 2011 by Mboutin (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Binary Hypothesis Testing

Decision Rule: A map from values of x to Ho or H1 if x E R, say H1 else if x does not contain R say Ho


Max-likelihood Rule:

Pick hypothesis that maxes conditional PDF

ML Rule: say H1 if fx|theta(x|theta1) > fx|theta0)

            H0 if fx|theta(x|theta1) <= fx|theta(theta|theta0)

Rml = {X such that fx|theta(x|theta1) > fx|theta(x|theta0}

Type I : Say H1 when truth is Ho Type II: say H0 when truth is H1

Probability of Type I : Pr(x E R|H0) Probablitiy of Type II: Pr(X E Rc|H1)


Back to ECE302 Fall 2008 Prof. Sanghavi

Alumni Liaison

Ph.D. on Applied Mathematics in Aug 2007. Involved on applications of image super-resolution to electron microscopy

Francisco Blanco-Silva