This research project is in progress. PCORI will post the research findings on this page within 90 days after the results are final.
One of PCORI’s goals is to improve the methods that researchers use for patient-centered outcomes research. PCORI funds methods projects like this one to better understand and advance the use of research methods that improve the strength and quality of comparative effectiveness research.
What is the project about?
In cluster randomized trials, or CRTs, researchers assign clusters of patients, like clinics or nursing homes, to different treatments by chance to compare the benefits and harms. One type of CRT is a stepped-wedge CRT, in which treatment groups start treatment at different times, or steps, during the study. Sometimes researchers may not have the resources or may decide not to follow all groups or collect data at every step. This is called an incomplete stepped-wedge design. Little guidance exists to help researchers plan for stepped-wedge CRTs and decide whether a complete or incomplete design would be best.
In this project, the research team is developing new methods to identify the best design and analyze data for stepped-wedge CRTs.
How can this project help improve research methods?
Results may help researchers when considering ways to design stepped-wedge CRTs.
What is the research team doing?
First, the research team is developing methods to help plan CRTs. The methods help calculate information such as how well the study can detect a treatment effect. Also, the methods help figure out how much the treatment effect might change if certain parts of a CRT change, such as the number of clusters. The methods can work with different types of data and analyses.
Second, the research team is developing software to analyze treatment effects for stepped-wedge CRTs. The software helps select ways to conduct analyses based on the type of study design and data. It can also account for aspects of the study that may influence the results, such as the number and size of groups.
Research methods at a glance
|Goal||To develop new methods and software to help plan and analyze incomplete stepped-wedge CRTs|
|Approach||Development of: statistical power procedures and formulae using cluster period summary statistics for different outcomes in complete and incomplete stepped wedge design; ratio of variance of the treatment effect when data elements are omitted to the variance when elements are included (generalized information content); treatment effect analysis software that considers within-cluster correlation structures, extends cluster deletion diagnostics, and includes bias corrections|