The RECPAM methodology previously presented in part I (A. Ciampi et al., Comput. Methods Programs Biomed. 26 (1988) 239-256) is applied to the analysis of survival data on small cell carcinoma of the lung (SCCL). It is shown how RECPAM can help answer the following questions which occur frequently in the analysis of clinical data: Is it possible to find a classification of patients with a certain disease into distinct prognostic groups? Given a covariate of special interest, does it have an independent prognostic significance even after confounding is taken into account? Does the prognostic significance of a covariate of special interest vary across patient subgroups? For the SCCL data, a prognostic classification is obtained and the tumor marker LDH is treated as a variable of special interest. Many features of RECPAM are illustrated, including, among others, Forward and Backward (Pruning) Stopping Rules, treatment of missing data, and use of several dissimilarity measures.