To learn more about the dilated form of cardiomyopathy associated with obesity, we conducted a pooled analysis of data from two case-control studies of idiopathic dilated cardiomyopathy. Up to two controls of the same sex and approximate age (+/- 5 years) had been selected for each case using random digit dialing. The subjects had been interviewed by telephone. We compared the cases (N = 224) and controls (N = 353) using conditional logistic regression. We defined severe obesity using national criteria for severely elevated body mass index. We found little association with severe obesity in multivariate analysis (relative odds = 1.1; 95% confidence interval = 0.7-1.9).