Method of characterizing the similarity between the entities of the measurements, a computer program and data carrier

摘要

PROBLEM TO BE SOLVED: To provide a method for efficiently characterizing similarity between measurement values of a plurality of entities.;SOLUTION: The method for characterizing similarity between the measurement values of a plurality of entities including the first entity and the second entity includes a step for receiving measurement values taken at a plurality of measurement points in each entity. A model provided with a probability process, a set of parameters and a model function having values depending on the measurement points is defined. Then a set (β) of parameters is estimated by fitting the model function to the measurement values. In a succeeding step, residual data are determined at least on a part of the plurality of measurement points for the first entity and the second entity by subtracting the fitted function from the measurement values. Then, a correlation coefficient of the first entity (i') and the second entity (i") is estimated based on the determined residual data and the estimated correlation coefficient is used to characterize the similarity between the measurement values. In the method, the model is defined so that the residual data are expected to have a deterministic component for controlling an estimation value of the correlation coefficient depending on the measurement points. The correlation coefficient is estimated by using an estimation value of an entity average residual averaged by the measurement points of the first entity and an estimation value of an entity average residual averaged by the measurement points of the second entity.;COPYRIGHT: (C)2009,JPO&INPIT