A review of the application of propensity score methods推荐.pdfVIP

NIH Public Access Author Manuscript J Clin Epidemiol . Author manuscript; available in PMC 2007 May 1. N Published in final edited form as: I H J Clin Epidemiol . 2006 May ; 59(5): 437–447. - P A A A review of the application of propensity score methods yielded u t h increasing use, advantages in specific settings, but not o r M substantially different estimates compared with conventional a n u s multivariable methods c r i p t Til Stürmer, MD, MPH1,2, Manisha Joshi, MS, MSW1, Robert J. Glynn, PhD, ScD1,2, Jerry Avorn, MD 1, Kenneth J. Rothman, DrPH1,3, and Sebastian Schneeweiss, MD, ScD1 1 Division of Pharmacoepidemiology and Pharmacoeconomics, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA 2 Division of Preventive Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA N I H 3 Department of Epidemiology, Boston University School of Public Health - P A Abstract A u Objective—Propensity score analyses attempt to control for confounding in non-experimental t h o studies by adjusting for the likelihood that a given patient is exposed. Such analyses have been r proposed to address confounding by indication, but there is little empirical evidence that they achieve M a better control than conventional multivariate outcome modeling. n u Study design and methods—Using PubMed and Science Citation Index, we assessed the use s c of propensity scores over time and critically evaluated studies published through 2003. r i p t Res