Effectiveness research and implications for study design: Sample size and statistical power

Most clinical trials have started to incorporate more broadly defined outco me measures, such as health-related quality of life, to complement clinical status measures as well as direct costs and cost-effectiveness analyses. C ontrasting a broad range of outcome and cost measures, we analyze the impli cations for sample sizes and study design using data from prior mental heal th and primary care studies that span a wide range of practice settings, pa tient populations, and geographic areas. While meaningful clinical symptoma tic differences are often detectable with sample sizes of well under 100 pe r cell, detecting even large changes in health-related quality of life gene rally requires several hundred observations per cell. Reasonable precision in cost estimates usually requires sample sizes in the thousands. Very few clinical trials or observational effectiveness studies that incorporate qua lity of life or cost measures have such sample sizes, resulting in many (un reported) null findings and, due to publication biases favoring significant results, scientific publications that exaggerate true effects. It raises i ssues for the general direction of clinical trials and effectiveness studie s, as well as for how cost and health-related quality of life results based on small studies should be dealt with in publications. (C) 1999 Elsevier S cience Inc.