Sample size requirements for prospective studies, with examples for coronary heart disease

J Clin Epidemiol. 1989;42(7):639-48. doi: 10.1016/0895-4356(89)90007-3.


Methods of determining the required number of disease cases for estimation of relative odds in prospective studies are evaluated, with examples from coronary heart disease. Data from a British prospective study of coronary heart disease are used in simulation exercises to assess the reliability of estimation formulae for both continuous and categorical risk factors. For continuous risk factors, a univariate formula based on estimation of the standardized relative odds (Whittemore A. S. JAMA 1981; 76: 27-32 [1]), gives reliable estimation of the required number of disease cases, provided the risk factor has a near normal distribution. An extension of the formula to adjustment for other risk factors, was less satisfactory, perhaps because of departures from multivariate normality. For categorical risk factors, an adaption of a univariate method for case control studies (Smith PG, Day NE. Int J Epidemiol 1984; 13: 356-365 [2]), gives reliable estimates of the number of cases required. However, this depends on approximate prior knowledge of the relative odds. In general, prospective studies of coronary heart disease risk factors should aim for at least 400 cases to enable sufficient accuracy of estimation.

MeSH terms

  • Adult
  • Alcohol Drinking
  • Cholesterol, HDL / blood
  • Coronary Disease / etiology*
  • Humans
  • Hypertension / complications
  • Male
  • Middle Aged
  • Prospective Studies*
  • Research Design*
  • Risk Factors
  • Sampling Studies
  • Smoking / adverse effects


  • Cholesterol, HDL