Disclosed are methods for analyzing the effect of a test substance on biological and/or biochemical samples in which a plurality of samples, each comprising a known concentration of the test substance in at least three different concentrations, are used to obtain measurements which provide raw data. An evaluation rule utilizes the raw data of the sample determining the effect of the test substance, at the particular concentration, on the sample. The evaluation rule is influenced by at least one control parameter, and at least one starting value for the at least one control parameter is determined. The raw data is evaluated and correspondence between the determined activities and a functional model resulting from theoretical considerations yields a dose/effect curve describing the dependence of the activities on the concentration of the test substance. The steps are modified and repeated until an abort criterion has been reached.