如何使?R語?做meta分析中的敏感性分析敏感性分析對(duì)于library(meta)data(Fleiss93)m1<-metabin(event.e,n.e,event.c,n.c,data=Fleiss93,studlab=study,sm="RR",method="I")m1metainf(m1)metainf(m1,pooled="random")forest(metainf(m1))forest(metainf(m1),layout="revman5")forest(metainf(m1,pooled="random"))metainf(m1,sortvar=study)metainf(m1,sortvar=7:1)m2<-update(m1,title="Fleiss93meta-analysis",backtransf=FALSE)metainf(m2)Loading'meta'package(version4.9-5).Type'help(meta)'forabriefoverview.RR95%-CI%W(fixed)%W(random)MRC-10.7420[0.5223;1.0543]2.47.8CDP0.6993[0.4828;1.0129]2.17.2MRC-20.8270[0.6487;1.0545]4.913.6GASP0.8209[0.5269;1.2789]1.55.3PARIS0.8193[0.5927;1.1326]2.88.9AMIS1.1183[0.9411;1.3289]9.720.4ISIS-20.9142[0.8596;0.9722]76.636.8Numberofstudiescombined:k=7RR95%-CIzp-valueFixedeffectmodel0.9137[0.8658;0.9643]-3.280.0010Randomeffectsmodel0.8929[0.8006;0.9959]-2.030.0419Quantifyingheterogeneity:tau^2=0.0074;H=1.29[1.00;1.98];I^2=39.6%[0.0%;74.6%]Testofheterogeneity:Qd.f.p-value9.9360.1277Detailsonmeta-analyticalmethod:-Inversevariancemethod-DerSimonian-Lairdestimatorfortau^2Influentialanalysis(Fixedeffectmodel)RR95%-CIp-valuetau^2I^2OmittingMRC-10.9183[0.8696;0.9698]0.00220.007441.5%OmittingCDP0.9190[0.8703;0.9705]0.00240.006036.6%OmittingMRC-20.9185[0.8691;0.9706]0.00250.010045.9%OmittingGASP0.9152[0.8669;0.9663]0.00140.009548.5%OmittingPARIS0.9166[0.8679;0.9680]0.00180.009547.3%OmittingAMIS0.8940[0.8447;0.9462]0.00010.00000.0%OmittingISIS-20.9124[0.8162;1.0199]0.10660.021449.6%Pooledestimate0.9137[0.8658;0.9643]0.00100.007439.6%Detailsonmeta-analyticalmethod:-InversevariancemethodInfluentialanalysis(Randomeffectsmodel)RR95%-CIp-valuetau^2I^2RR95%-CIp-valuetau^2I^2OmittingMRC-10.9071[0.8098;1.0162]0.09240.007441.5%OmittingCDP0.9124[0.8201;1.0151]0.09210.006036.6%OmittingMRC-20.8983[0.7907;1.0204]0.09910.010045.9%OmittingGASP0.8931[0.7922;1.0068]0.06430.009548.5%OmittingPARIS0.8963[0.7929;1.0131]0.07990.009547.3%OmittingAMIS0.8940[0.8447;0.9462]0.00010.00000.0%OmittingISIS-20.8596[0.7249;1.0194]0.08200.021449.6%Pooledestimate0.8929[0.8006;0.9959]0.04190.007439.6%Detailsonmeta-analyticalmethod:-Inversevariancemethod-DerSimonian-Lairdestimatorfortau^2Influentialanalysis(Fixedeffectmodel)RR95%-CIp-valuetau^2I^2OmittingAMIS0.8940[0.8447;0.9462]0.00010.00000.0%OmittingCDP0.9190[0.8703;0.9705]0.00240.006036.6%OmittingGASP0.9152[0.8669;0.9663]0.00140.009548.5%OmittingISIS-20.9124[0.8162;1.0199]0.10660.021449.6%OmittingMRC-10.9183[0.8696;0.9698]0.00220.007441.5%OmittingMRC-20.9185[0.8691;0.9706]0.00250.010045.9%OmittingPARIS0.9166[0.8679;0.9680]0.00180.009547.3%Pooledestimate0.9137[0.8658;0.9643]0.00100.007439.6%Detailsonmeta-analyticalmethod:-InversevariancemethodInfluentialanalysis(Fixedeffectmodel)RR95%-CIp-valuetau^2I^2OmittingISIS-20.9124[0.8162;1.0199]0.10660.021449.6%OmittingAMIS0.8940[0.8447;0.9462]0.00010.00000.0%OmittingAMIS0.8940[0.8447;0.9462]0.00010.00000.0%OmittingPARIS0.9166[0.8679;0.9680]0.00180.009547.3%OmittingGASP0.9152[0.8669;0.9663]0.00140.009548.5%OmittingMRC-20.9185[0.8691;0.9706]0.00250.010045.9%OmittingCDP0.9190[0.8703;0.9705]0.00240.006036.6%OmittingMRC-10.9183[0.8696;0.9698]0.00220.007441.5%Pooledestimate0.9137[0.8658;0.9643]0.00100.007439.6%Detailsonmeta-analyticalmethod:-InversevariancemethodReview:Fleiss93meta-analysisInfluentialanalysis(Fixedeffectmodel)logRR95%-CIp-valuetau^2I^2OmittingMRC-1-0.0852[-0.1397;-0.0307]0.00220.007441.5%OmittingCDP-0.0844[-0.1389;-0.0300]0.00240.006036.6%OmittingMRC-2-0.0850[-0.1403;-0.0298]0.00250.010045.9%OmittingGASP-0.0886[-0.1429;-0.0343]0.00140.009548.5%OmittingPARIS-0.0871[-0.1417;-0.0325]0.00180.009547.3%OmittingAMIS-0.1120[-0.1687;-0.0553]0.00010.00000.0%OmittingISIS-2-0.0917[-0.2031;0.0197]0.10660.021449.6%Pooledestimate-0.0902[-0.1441;-0.0363]0.00100.007439.6%Detailsonmeta-analyticalmethod:-InversevariancemethodInfluentialanalysis(Fixedeffectmodel)SMD95%-CIp-valuetau^2I^2Omitting1-0.3439[-0.6239;-0.0638]0.01610.020018.4%Omitting2-0.2359[-0.5567;0.0848]0.14940.00000.0%Omitting3-0.3632[-0.6808;-0.0456]0.02500.024717.3%Omitting4-0.4464[-0.7373;-0.1555]0.00