This article describes and discusses the strengths and limitations of the major pharmacoepidemologic methodologies employed in postmarketing drug surveillance and describes the current status of the U.S. surveillance system. The main methodologies employed in postmarketing drug surveillance include controlled clinical trials, observational epidemiologic studies (cohort, case-control, cross-sectional), demographic methods, drug utilization surveys, spontaneous reports, and automated databases linking medications and disease. Examples of pharmacoepidemiologic studies using each of these methodologies are presented. When a question arises about the efficacy and/or safety of a marketed drug, typically a mixture of these study methodologies is employed. The article concludes with a brief discussion of the role of the Food and Drug Administration, pharmaceutical manufactures, and academic institutions in initiating and conducting postmarketing drug studies.