The objectives of this NIHR HTA funded study were firstly to consider the effects of contamination on the magnitude and statistical significance (or precision) of the estimated randomised trial effect size of an educational intervention. Secondly, to investigate the mechanisms of contamination and to consider how contamination can be avoided.
The study found little evidence that contamination really is a problem in trials of educational interventions in health because very few studies reported whether contamination occurred. However, there is consensus about the types of situation in which contamination is more or less likely. If it is likely then cluster randomisation may reduce contamination unless entire clusters are contaminated. Causal model analysis may reduce bias if contamination is measured. In future trials of educational interventions in health, it is a priority to report the extent, nature and effects of contamination.
Craig Ramsay; firstname.lastname@example.org
Keogh-Brown MR, Bachmann MO, Shepstone L, Hewitt C, Howe A, Ramsay CR, et al. Contamination in trials of educational interventions. Health Technol Assess 2007;11(43).