The estimation of the model order in exponential families

Abstract

Estimators are sought that achieve high exponential rate of decrease in the underestimation probability while keeping the overestimation probability exponent at a certain prescribed level. It is assumed that a given integer is known to upper-bound the true order. Some examples are given of possible applications of the proposed method in specific order estimation and hypothesis testing problems.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>