We examined the associations of colon cancer with constipation and use of commercial laxatives in a case-control study among men and women ages 30–62 years. We based this analysis on 424 incident cases of colon cancer, diagnosed in the Seattle metropolitan area between 1985 and 1989, and 414 random-digit-dial controls. Frequent constipation during the 10 years before the reference date (2 years before diagnosis), as defined by “feeling constipated to the point of having to take something,” was associated with substantially increased risk of colon cancer. The adjusted relative risk (RR) was 2.0 [95% confidence interval (CI) = 1.2–3.6] for constipation 12–51 times per year, and 4.4 (95% CI = 2.1–8.9) for constipation 52 or more times a year. Cumulative lifetime use of commercial laxatives was also associated with increased risk of colon cancer. When constipation and commercial laxative use were adjusted for each other, the association with commercial laxative use disappeared, whereas the association with constipation remained strong. Although constipation has not consistently been associated in past studies with a large increase in risk of colon and rectal cancer combined, these results suggest that frequent constipation may be an important risk factor for colon cancer among middle-aged adults. (Epidemiology 1998; 9:385–391)