Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Maarten Buis <maartenlbuis@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Capability of the margins command |
| Date | Sun, 18 Aug 2013 09:51:04 +0200 |
Cox regression is a semi-parametric approach in that it does not estimate the baseline hazard function. This is a strength in that you cannot make a mistake in something you don't model, but it is also a weakness in that it makes it hard to draw conclusions on anything other than the hazard ratio. So, it unfortunately fits the logic of Cox regression that it does not work well with commands like -margins-. I don't say that what -margins- produces is wrong, I suspect that it just does not mean what you think it means. To see what is exactly predicted you will have to look at the predictions in -help stcox_postestimation-. I doubt however that it will give you what you want. -- Maarten On Fri, Aug 16, 2013 at 11:11 PM, Kai Huang <demonsecret@hotmail.com.hk> wrote: > Dear all, > > The help file of --margins-- command has the following description: > > "The margins command estimates margins of responses for specified values of covariates and presents the results as a table. > > Capabilities include estimated marginal means, least-squares means, average and conditional marginal and partial effects (which may be reported as derivatives or as elasticities), > average and conditional adjusted predictions, and predictive margins." > > I would like to ask whether --margins-- is capable of estimating the marginal effects of the estimates generated from --stcox--. I have tried and found that the magnitude of the results are very different from those generated in hazard ratios from --stcox--. > > > Thank you very much in advance. > > Best regards, > Kai Huang > * > * 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/ -- --------------------------------- Maarten L. Buis WZB Reichpietschufer 50 10785 Berlin Germany http://www.maartenbuis.nl --------------------------------- * * 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/