Characterization of methods for surveillance by optimality

Abstract

Different criteria of optimality are discussed. The shortcomings of some criteria of optimality are demonstrated by their implications. The correspondences between some criteria of optimality and some methods are examined. The situations and parameter values for which some commonly used methods have certain optimality properties are thus illuminated. A linear approximation of the full likelihood ratio method, which satisfies several criteria of optimality, is presented. This linear approximation is used for comparisons with the exponentially weighted moving average method. Via these comparisons it is possible to illuminate the influence of different criteria of optimality on the "optimal" parameter of a method. A uniform presentation of methods, by expressions oflikelihood ratios, facilitates the comparisons between methods.