a1 New York State Psychiatric Institute and Columbia University, New York, USA
An appropriate choice of controls in case/control studies of specific psychiatric disorders is crucial for valid risk-factor assessment. One suggested approach to control-group selection, the use of a well control group, is the focus of this paper. While using well controls has intuitive appeal, this paper shows that such a procedure can lead to ambiguous and biased results.
c1 Address for correspondence: Dr Sharon Schwartz, Social Psychiatry Research Unit, Columbia University, 100 Haven Avenue, Tower III 19E, New York, New York 10032, USA.