Session Information
09 SES 12 B, Methodological Issues in Tests and Assessments
Paper Session
Contribution
Researchers often want to estimate the effect of an intervention. The method of preference for doing this is to conduct a randomized experiment. However, in field research, random assignment is not always feasible or ethical. The intervention may have already been implemented before the researcher starts the study or ethical principles may restrain placing eligible participants to an intervention group at random. As a result, people may self-select or be selected on non-random basis into cases or controls in various kinds of quasi-experimental designs. Traditional statistical methods exist to adjust for group differences such as regression/ANCOVA or matching but when assignment to intervention is based on a large number of variables these adjustment methods become complicated. The propensity score is a relatively new statistical method to estimate intervention effects. The propensity score reduces all the measured variables (x) that are related to the probability to treatment assignment (z=1) to a single number, e(x). The purpose of a propensity score is to create comparable groups in observational studies by removing or reducing the bias that may be attributed to assignment to intervention. The propensity score produces a new sample with comparable groups to use when estimating intervention effects. Individuals in the intervention or the control groups with the same propensity score are said to be balanced on the measurement covariates. The use and application of propensity scores in psychological and educational research has been steeply rising in the last 3 years. This trend illustrates that there is a call for a tool to measure causal intervention effects in observational studies. The purpose of this paper is to give a brief introduction of the concept of propensity score and to give an example of the application of the propensity score in the research project of placing Finnish children into foster care during WWII.
Method
Expected Outcomes
References
Bellara, A. P. & Kim, E. S. Using propensity scores to estimate effects. http://www.coedu.usf.edu/cream/documents/PPPropensity_score_workshop_Bellara_and_Kim.pdf. Luellen, J. K., Shadish, W. R. & Clark, M. H. 2005. Propensity score: An introduction and experimental test. Evaluation Review, 29, 530-558. Rosenbaum, P. R., & Rubin, D. B. 1983. The central role of the propensity score in observational studies for causal effects, Biometrica, 70, 41-55. Thoemmets, F. J. & Kim, E. S. 2011. A systematic review of propensity score methods in the social sciences. Multivariate Behavioral Research, 46, 90-118.
Search the ECER Programme
- Search for keywords and phrases in "Text Search"
- Restrict in which part of the abstracts to search in "Where to search"
- Search for authors and in the respective field.
- For planning your conference attendance you may want to use the conference app, which will be issued some weeks before the conference
- If you are a session chair, best look up your chairing duties in the conference system (Conftool) or the app.