A response time model for drug surveillance

Abstract For the purpose of drug surveillance, i.e., for continuous evaluation of possible associations between drugs and pathological manifestations (events), a response time model is suggested which involves the time of first drug administration and the event appearance time. Explicit parameter estimates can be easily computed from samples of such times which are extracted from routine medical records. The estimates enter a test statistic Δ, the performance of which has been evaluated by Monte Carlo exploration. A numerical example, association between Penicillin and “Rass,” demonstrates the test. Generally, the procedure might be useful in areas of investigation where the times of emergence of two phenomena can be observed and the question of their dependence is under study.