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.
This research project is in progress. PCORI will post the research findings on this page within 90 days after the results are final.
What is the research about?
Researchers use stated choice experiments, or SCEs, to help understand patient preferences. SCEs give people a series of health scenarios with different options to choose from. People choose which option they prefer at each step. For example, people might be asked to choose between two mock organ donation recipients with different traits, such as organ donor status or whether they have dependents. SCEs allow researchers to see people’s preferences between traits, such as whether they favor recipients with or without dependents, and how much each trait affects choices. This information can be used to predict what people are likely to choose when asked to make a trade-off, such as whether they may be likely to choose to use a new treatment.
Current methods for conducting SCEs have some drawbacks. For example, to get an accurate idea of what people prefer, researchers need to start with a pilot survey of a small group. But it may be hard to know how large the pilot sample should be and, as a result, some SCEs don’t start with enough people for results to be reliable. Also, when one person answers several different questions, the responses vary less than if a different person completes each question. SCEs don’t usually take this into account. Finally, the way researchers design SCEs can make it hard to measure people’s preferences accurately. For example, if a survey is too long or the choices are too difficult, people might take shortcuts instead of thinking through all the options.
In this study, the research team wants to improve methods for conducting SCEs. The team is creating a way to calculate the proper sample size for pilot SCE studies. In addition, the team is developing methods to get more precise results from SCE studies using a statistical approach called bootstrapping. The team is also figuring out how setting up SCEs in different ways could make the results more or less accurate.
Who can this research help?
Results may help researchers design SCEs that produce precise results and accurately describe patients’ preferences.
What is the research team doing?
In this study, the research team is running simulations using data from four real SCEs. The simulations use computers to test many different scenarios, allowing researchers to compare new methods with existing methods. The simulations include realistic choices for each of the actual steps in SCE studies such as
- Choosing a statistical approach
- Setting up choice tasks
- Selecting a sample
- Conducting the pilot study
- Adjusting the choice tasks
- Conducting the main study
For example, the simulations include different choices for sample-size formulas and set up choice tasks in different ways. By simulating each set of design choices hundreds or thousands of times, the team can see how well their sample-size formula, design choices, and bootstrapping methods work.
Research methods at a glance
- No information provided by awardee.
Other Stakeholder Partners
- Emily Lancsar, Monash University, Clayton, Victoria, Australia
- Esther de Bekker-Grob, Erasmus MC, Rotterdam, Netherlands
- Mandy Ryan, University of Aberdeen, Foresterhill, Aberdeen, United Kingdom