Abstract

In an era of chronic resource scarcity it is critical that quality improvement professionals have confidence that their project activities cause measured change. A commonly used research design, the single group pre-test/post-test design, provides little insight into whether quality improvement interventions cause measured outcomes. A re-evaluation of a quality improvement programme designed to reduce the percentage of bilateral cardiac catheterisations for the period from January 1991 to October 1996 in three catheterisation laboratories in a north eastern state in the USA was performed using an interrupted time series design with switching replications. The accuracy and causal interpretability of the findings were considerably improved compared with the original evaluation design. Moreover, the re-evaluation provided tangible evidence in support of the suggestion that more rigorous designs can and should be more widely employed to improve the causal interpretability of quality improvement efforts. Evaluation designs for quality improvement projects should be constructed to provide a reasonable opportunity, given available time and resources, for causal interpretation of the results. Evaluators of quality improvement initiatives may infrequently have access to randomised designs. Nonetheless, as shown here, other very rigorous research designs are available for improving causal interpretability. Unilateral methodological surrender need not be the only alternative to randomised experiments.