OBJECTIVE To estimate the cost-effectiveness of 5 years of treatment with hormone therapy (HT) compared with no treatment for women with menopausal symptoms in the United States. METHODS A Markov cohort simulation model was used with tunnel techniques to assess the cost-effectiveness of HT in women aged 50 years, based on a societal perspective. Clinical data, where possible, used results taken from the Women Health Initiative (WHI). The model had a lifetime horizon with cycle lengths of 1 year and contained the following disease states: hip fracture, vertebral fracture, wrist fracture, breast cancer, colorectal cancer, coronary heart disease, stroke, and venous thromboembolic events. An intervention was modelled by its impact on the disease risks during and after stopping treatment. The model required data on clinical effects, risks, mortality rates, quality of life weights, and costs. The main outcome of the model was cost per quality-adjusted life-year (QALY) gained on HT compared with no treatment. RESULTS The results indicated that it was cost-effective to treat women with menopausal symptoms with HT in the United States. The severity of menopausal symptoms was the single most important determinant of cost-effectiveness, but HT remained cost-effective even where symptoms were mild or effects on symptom relief were small. CONCLUSIONS Treatment of women with menopausal symptoms with HT is cost-effective.