Psychiatric genetic epidemiology has, as a field, undergone considerable change in the last two decades. My goal here is to provide a brief, selective and inevitably personal overview of where the field has come from, where it is now and where it might be going. Methodologic issues will be emphasized, particularly those of an "epidemiologic" nature. I will organize this review around three of the major methods used in psychiatric genetics: family studies, twin studies and linkage studies.