Sensitivity of searches for new signals and its optimization
Abstract
Description
A frequentist definition of sensitivity of a search for new phenomena is discussed, that has several useful properties. It is based on completely standard concepts, is generally applicable, and has a very clear interpretation. It is particularly suitable for optimization, being independent of a-priori expectations about the presence of a signal, thus allowing the determination of a single set of cuts that is optimal both for setting limits and for making a discovery. Simple approximate formulas are given for the common problem of Poisson counts with background.
Talk from PhyStat2003, Stanford, Ca, USA, September 2003, PSN MODT002. 5 pages, LaTeX, 6 eps figures. Reformatted according to conference style, small improvements in text and figures
Talk from PhyStat2003, Stanford, Ca, USA, September 2003, PSN MODT002. 5 pages, LaTeX, 6 eps figures. Reformatted according to conference style, small improvements in text and figures