Scientific criticism when analyzed in depth, appears to be as exacting as ethical criticism of statistics relating to adjuvant therapy comparative trial results, based on survival or on length of first remission. The heterogeneity of a population in which an exponential curve represents survival or period of disease-free survival (OFS) raises the issue of the significance of a benefit or absence of benefit provided by studied treatment. The segmentation of exponential curves into two or three slopes is proposed. This permits a more accurate evaluation of the results, as well as the application of several protocols, adapted to separate homogeneous groups of patients.