Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | mccali mccalister <mccali85@hotmail.com> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | st: McNEMAR test or Average treatment effects in matched data. |
| Date | Thu, 2 Jan 2014 19:13:11 +0000 |
Hi, I need some help with matched paired data. I am working with pared data using PSMATCH2 and TEFFECTS. I do get well balanced data checked with PSTEST. But I do have a question comparing the effect of the treatment ( the reduction of mediastinitis in cardiac surgery ). What should I use? a McNemar test weighted by PSmatch2 ( I did NN-K, 5:1), or should I use simply the ATE, ATET or ATU that I get in the Teffects or Psmatch2. Maybe both are 2 things conceptualy different? All my data are binomial Best regards happy new Year to Every One Dr.Ayaon Albarran Cardiovascular resident * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/