Abstract
Colorectal cancer (CRC) is the third leading type of cancer and the third leading cause of cancer death in the United States. National policy-making organizations recognize and support a variety of CRC screening strategies among average-risk adults aged 50 and older based on strong evidence showing that screening decreases mortality from CRC and can also reduce the incidence of the disease. The goal of this study was to test a multi-level stepped intervention to increase CRC screening rates. We used a group-randomized trial design where the units of assignment were clinics and the units of observation were eligible patients receiving care at those clinics, with stratified random assignment of clinics to study conditions. The primary analysis was planned as a mixed-model logistic regression to account for the expected positive intraclass correlation associated with clinics. Our recruitment experience reflected the difficulties of conducting research in the real world where changes in economic conditions, staff turnover/layoff, inadequate medical records, and poor acceptance of research can significantly impact study plans. It demonstrated the problems that can emerge when procedures used in the study depart from those used in the pilot work to generate parameter estimates for power analysis. It also demonstrated the importance of allowing for attrition at the group and patient levels so that if recruitment falls short, it is possible to maintain adequate power with only a slight increase in the detectable difference. This experience should assist others planning group-randomized trials, whether in cancer screening or in other areas.