American Statistical Association
Observational studies are a primary research method for comparative effectiveness research and patient-centered outcomes research. Their utility, however, is restricted by the fact that treatment choice is affected by known or unknown prognostic factors. This situation known as confounding by indication for treatment may render observational studies invalid and irrelevant unless properly addressed. Proper treatment of confounding is further complicated in data obtained from registries, network databases or the Electronic Health Record where subjects or patients are commonly clustered in ways that may be relevant to the analysis. We extend propensity score matching methodology to address measured and unmeasured confounding at the cluster level.
|Date:||Wednesday, October 3, 2018|
|Time:||4:00 - 5:00 P.M.|
Memorial Sloan Kettering Cancer Center
Department of Epidemiology and Biostatistics
485 Lexington Avenue
(Between 46th & 47th Streets)
2nd Floor, Conference Room B
New York, New York
**Outside visitors please email email@example.com for building access.
You must be on the security list to enter the floor.