资源描述：
《r语言中的t-test和anova.ppt》由会员上传分享，免费在线阅读，更多相关内容在教育资源-天天文库。
1、R语言中的t-test和ANOVA组员：程琪张君颀周祎炜IndexT-testANOVA单因子方差分析同时置信区间双因子方差分析有交互作用的方差分析多重t-test分析Vasishth’sHeightExampleSAMP={53.56797,60.12001,59.85700,63.53580,62.00390,61.80454,64.33530,61.38428,60.05831,65.93938,57.21961}Shrinkingdrug(non-effectvalue=64)大部分情况下我们并不知道σ——T分布>pt(-3.02,df=10)+(1-pt(3.
2、02,df=10))[1]0.01289546Vasishth’sHeightExampleThep-valueofthistwo-sidedt-testis0.012.>samp<-c(53.56797,60.12001,59.857,63.5358,62.0039,61.80454,+64.3353,61.38428,60.05831,65.93938,57.21961)>t.test(samp,mu=64)OneSamplet-testdata:sampt=-3.0237,df=10,p-value=0.01281alternativehypothesis:tru
3、emeanisnotequalto6495percentconfidenceinterval:58.6039663.18260sampleestimates:meanofx60.89328>source(file="shade.tails.R")>shade.tails(3.02,tail="both",df=10)曲线下小于-3.02只有0.06%通过KeithJohnson’sshade.tails这个功能绘图.t.test()的调用格式t.test(x,y=NULL,alternative=c("two.sided","less","greater"),mu=0,
4、paired=FALSE,var.equal=FALSE,conf.level=0.95,...)若仅出现数据x,则进行单样本t检验;若出现数据x和y,则进行二样本的t检验alternative=c("two.sided","less","greater")用于指定所求置信区间的类型;alternative="two.sided"是缺省值,表示求置信区间alternative="less"表示求置信上限;alternative="greater"表示求置信下限.mu表示均值,它仅在假设检验中起作用,默认值为零.单正态总体参数检验>x<-c(175,176,173,175
5、,174,173,173,176,173,179)>t.test(x)OneSamplet-testdata:xt=283.8161,df=9,p-value<2.2e-16alternativehypothesis:truemeanisnotequalto095percentconfidenceinterval:173.3076176.0924sampleestimates:meanofx174.7>t.test(x)$conf.int#置信区间[1]173.3076176.0924attr(,"conf.level")[1]0.95两正态总体参数检验>x<-c(20
6、.5,19.8,19.7,20.4,20.1,20.0,19.0,19.9)>y<-c(20.7,19.8,19.5,20.8,20.4,19.6,20.2)>t.test(x,y,var.equal=TRUE)TwoSamplet-testdata:xandyt=-0.8548,df=13,p-value=0.4081alternativehypothesis:truedifferenceinmeansisnotequalto095percentconfidenceinterval:-0.76842490.3327106sampleestimates:meanofxm
7、eanofy19.9250020.14286原假设的显著性检验>x<-c(20.5,18.8,19.8,20.9,21.5,19.5,21.0,21.2)>y<-c(17.7,20.3,20.0,18.8,19.0,20.1,20.0,19.1)>t.test(x,y,paired=TRUE)Pairedt-testdata:xandyt=1.8002,df=7,p-value=0.1149alternativehypothesis:truedifferenceinmeansisnotequalto095percentconfidence
