Project Summary
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?
A randomized controlled trial, or RCT, is often the best way to learn if one treatment works better than another. RCTs assign patients to different treatments by chance. But RCTs are not always feasible. When they’re not, researchers can use observational studies, which look at what happens when patients and their doctors choose the treatments. But traits such as age or health status may affect treatment choices. These traits may also be linked to patients’ health, making it hard to know if changes in health are due to treatment or to patient traits.
To know how accurate the results of observational studies are, researchers can design analyses that mimic analyses of results from a completed RCT. Then, they can compare the results of the observational analysis to those from the RCT. Such a comparison is called benchmarking. When results of observational analyses are accurate, researchers may also choose to do a joint analysis. In joint analyses, researchers analyze RCT and observational data together. Doing so can help provide more precise estimates of treatment effects. But current methods for benchmarking and joint analysis are limited.
In this project, the research team is developing statistical methods to improve benchmarking and joint analysis.
How can this project help improve research methods?
Results may help researchers when considering ways to analyze data from observational studies.
What is the research team doing?
First, the research team is developing a framework for benchmarking observational analyses against RCTs. To do so, the team is using statistical methods for assessing cause and effect. Second, the team is building on the framework to develop new methods for joint analysis. The team is designing the methods to analyze data from one point in time and data from multiple points in time. Third, the team is testing the new methods on data created by a computer program to mimic real data. Finally, the team is using the new methods to analyze data from two RCTs of treatment for heart disease along with observational data from patient registries. Patient registries store data about people with a specific health problem.
Research methods at a glance
Design Element | Description |
---|---|
Goal |
|
Approach | Benchmarking, joint analysis, data-adaptive statistical methods, causal inference methods, framework development |