Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "b. water" <barleywater@hotmail.com> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | RE: st: Wanting to forest plot sensitivity and -LR for categorical outcomes |
Date | Mon, 22 Mar 2010 02:40:12 +0000 |
Ed, Ben Dwamena's website has a collection of tools: http://sitemaker.umich.edu/metadiagnosis/resources but if you are stuck and you still wish to do sensitivity and specificity forest plot, you can check out: http://www.hrc.es/investigacion/metadisc_en.htm you can copy and paste your author yr n tp fp fn tn to the tool to produce the required forest plots - it is however M$ Excel based. bw ---------------------------------------- > Date: Fri, 5 Mar 2010 22:08:11 -0800 > From: ed_speged@yahoo.com > Subject: st: Wanting to forest plot sensitivity and -LR for categorical outcomes > To: statalist@hsphsun2.harvard.edu > > Dear Stata listers, > I am hoping to create a forest plot of sensitivity and -LR using metandi. Unfortunately I believe I am not able to use MIDAS without Stata 10. Using Stata 8.2, I have a set of 14 studies of a diagnostic outcome with a categorical outcome. They are in the format author yr n tp fp fn tn > I am able to plot sROC, calcuate summary estimates of Se, Sp, -LR, DOR, etc and also have calculated the individual parameters for the Se and Sp (using metandi_p). I have reached a technical sticking point and am wondering if a kind person familiar with metandi can recommend the most time efficient way to either produce the variances for Se and Sp needed for the forest plot or just plot directly the graph itself. Or, if not perhaps an alternate method of estimating the variance. Thank you kindly in advance. Eddie > > > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ _________________________________________________________________ Hotmail: Trusted email with Microsoft’s powerful SPAM protection. http://clk.atdmt.com/GBL/go/210850552/direct/01/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/