SURVIVAL ANALYSIS WITH UNRELIABLE END-POINTS

There exists a current interest in the application of survival analysi s methodology to evaluate differences in latencies of response to psyc hological or psychopharmacological treatment modalities. However, unre liability in the measurement of treatment responses in such research p oses a problem. Two methods of defining the ''discrete endpoint'' that is required for survival analysis are compared regarding power of tes ts of significance for differences in survival curves. Discrete endpoi nts defined by regression equations fitted to all available data for e ach subject provided greater power when entered into survival analysis than did endpoints dependent only on individual measurements. While t his may not surprise statisticians, no examples of the use of regressi on estimates for survival analysis endpoints have been identified in r eports of previous Clinical trials nor in discussions concerning poten tial applications of survival analysis methodology in psychiatric rese arch. (C) 1997 Elsevier Science Ltd.