Results of premarketing and postmarketing trials have raised doubts about the cardiovascular safety of the non-steroidal anti-inflammatory drug (NSAID) rofecoxib, especially at doses greater than 25 mg. Between Jan 1, 1999, and June 30, 2001, we did a retrospective cohort study of individuals on the expanded Tennessee Medicaid programme (TennCare), in which we assessed occurrence of serious coronary heart disease (CHD) in non-users (n=202 916) and in users of rofecoxib and other NSAIDs (rofecoxib n=24132, other n=151728). Participants were aged 50–84 years, lived in the community, and had no life-threatening non-cardiovascular illness. Users of high-dose rofecoxib were 1·70 (95% Cl 0·98–2·95, p=0·058) times more likely than non-users to have CHD; among new users this rate increased to 1·93 (1·09–3·42, p=0·024). By contrast, there was no evidence of raised risk of CHD among users of rofecoxib at doses of 25 mg or less or among users of other NSAIDs.