Observational studies are a common and important aspect of critical care research. A key challenge in the design of observational studies is the control of confounding. Confounding arises when the groups being compared in a study have different baseline risks for the study outcome, resulting from an imbalance of risk factors between groups. The presence of confounding makes it difficult to determine whether observed differences in outcome are due to the exposure of interest, to the effect of the confounding factors, or a mixture of both. Propensity score analysis is a statistical method that controls confounding by balancing the distribution of confounding variables across groups being compared in a study. This webinar will provide an overview of the key steps involved in propensity score analysis for those interested in using propensity score analysis in their own research, and for readers of the critical care literature. This is a grant-sponsored webcast; it is complimentary for attendees.

Read More