1、R语言方法总结R语言方法总结计算描述性统计量:1、summary():例: summary(mtcarsvars)summary()函数提供了最小值、最大值、四分位数和数值型变量的均值,以及因子向量和逻辑型向量的频数统计。2、apply()函数或sapply()函数计算所选择的任意描述性统计量。mean、 sd、 var、 min、 max、 median、 length、 range和quantile。函数fivenum()可返回图基五数总括(Tukeys five-number summary,即最小值、下四分位数、中位数、上四分位数和最大值)。sapply() 例: mystats -
2、function(x, na.omit = FALSE) if (na.omit) x - x!is.na(x) m - mean(x) n - length(x) s - sd(x) skew - sum(x - m)3/s3)/n例: dstats - function(x)(c(mean=mean(x), sd=sd(x) by(mtcarsvars, mtcars$am, dstats) by(mtcars,vars,mtcars$am,plyr:colwis(dstats)3、summaryBy():doBy包例 library(doBy)summaryBy(mpg + hp + w
3、t am, data = mtcars, FUN = mystats)4、describe.by():doBy包(describe.by()函数不允许指定任意函数,)例:library(psych)describe.by(mtcarsvars, mtcars$am)5、reshape包分组:(重铸和融合)例:library(reshape)dstats - function(x) (c(n = length(x), mean = mean(x), sd = sd(x)dfm - melt(mtcars, measure.vars = c(mpg, hp, wt), id.vars = c(am
4、, cyl)cast(dfm, am + cyl + variable ., dstats)频数表和列联表1、table():生成简单的频数统计表mytable - with(Arthritis, table(Improved)Mytable2、prop.table():频数转化为比例值prop.table(mytable)3、prop.table()*100:转化为百分比prop.table(mytable)*100二维列联表4、table(A,B)/xtabs(A+b,data=mydata)例:mytable - xtabs( Treatment+Improved, data=Arthr
5、itis)5、margin.table()和prop.table():函数分别生成边际频数和比例 (1:行,2:列)行和与行比例margin.table(mytable, 1)prop.table(mytable, 1)列和与列比例margin.table(mytable, 2)prop.table(mytable, 2)prop.table(mytable)6、addmargins():函数为这些表格添加边际和addmargins(mytable)admargins(prop.table(mytable)addmargins(prop.table(mytable, 1), 2)addmarg
6、ins(prop.table(mytable, 2, 1)7.crossTable():gmodels包例:library(gmodels)CrossTable(Arthritis$Treatment, Arthritis$Improved)多维列联表1、table()和xtabs():都可以基于三个或更多的类别型变量生成多维列联表。2、ftable():例:mytable - xtabs( Treatment+Sex+Improved, data=Arthritis)mytableftable(mytable)margin.table(mytable, 1)margin.table(myta
7、ble, 2)margin.table(mytable, 3)margin.table(mytable, c(1,3)ftable(prop.table(mytable, c(1, 2)ftable(addmargins(prop.table(mytable, c(1, 2), 3)gtable(addmargins(prop.table(mytable, c(1, 2), 3) * 100独立检验1、卡方独立性检验 :chisq.test()例:library(vcd)mytable - xtabs(Treatment+Improved, data=Arthritis)chisq.test(
8、mytable)mytable - xtabs(Improved+Sex, data=Arthritis)chisq.test(mytable)2、Fisher精确检验:fisher.test() 例:mytable - xtabs(Treatment+Improved, data=Arthritis) fisher.test(mytable)3、Cochran-MantelHaenszel检验:mantelhaen.test() 例:mytable - xtabs(Treatment+Improved+Sex, data=Arthritis) mantelhaen.test(mytable)
9、相关性度量1、assocstats(): 例:library(vcd)mytable - xtabs(Treatment+Improved, data=Arthritis)assocstats(mytable)2、cor():函数可以计算这三种相关系数,3、cov():函数可用来计算协方差例:states - state.x77, 1:6cov(states)cor(states)cor(states, method=spearman)x - states, c(Population, Income, Illiteracy, HS Grad)y - states, c(Life Exp, Mu
10、rder)cor(x, y)4、pcor():偏相关 ggm包例:library(ggm)pcor(c(1, 5, 2, 3, 6), cov(states)相关性的显著性检验1、cor.test()其中的x和y为要检验相关性的变量, alternative则用来指定进行双侧检验或单侧检验(取值为two.side、 less或greater) ,而method用以指定要计算的相关类型(pearson、kendall或spearman)当研究的假设为总体的相关系数小于0时,请使用alternative=less。在研究的假设为总体的相关系数大于0时,应使用alternative=greater。
11、在默认情况下,假设为alternative=two.side(总体相关系数不等于0)。 例:cor.test(states, 3, states, 5)2、corr.test():可以为Pearson、 Spearman或Kendall相关计算相关矩阵和显著性水平。例:library(psych)corr.test(states, use = complete)3、pcor.test():psych包t 检验1、t.test(yx,data)(独立样本)例:library(MASS)t.test(Prob So, data=UScrime)2、t.test(y1,y2,paired=TRUE)
12、(非独立) 例:library(MASS)sapply(UScrimec(U1, U2), function(x) (c(mean = mean(x), sd = sd(x)with(UScrime, t.test(U1, U2, paired = TRUE)组间差异的非参数检验两组的比较:1、wilcox.test(yx,data) :评估观测是否是从相同的概率分布中抽得例:with(UScrime, by(Prob, So, median)wilcox.test(Prob So, data=UScrime)2、wilcox.test(y1,y2,paried=TRUE):它适用于两组成对数
13、据和无法保证正态性假设的情境。例:sapply(UScrimec(U1, U2), median)with(UScrime, wilcox.test(U1, U2, paired = TRUE)多于两组的比较:1、kruskal.test(yA,data):各组独立例:states - as.data.frame(cbind(state.region, state.x77)kruskal.test(Illiteracy state.region, data=states)2、friedman.test(yA|B,data):各组不独立非参数多组比较:1、npmc() :npmc包例:class
14、 - state.regionvar - state.x77, c(Illiteracy)mydata - as.data.frame(cbind(class, var)rm(class,var)library(npmc)summary(npmc(mydata), type = BF)aggregate(mydata, by = list(mydata$class), median)回归用一个或多个预测变量(也称自变量或解释变量)来预测响应变量(也称因变量、效标变量或结果变量)的方法。1、lm(): 拟合回归模型 lm(yx1+x2+x3,data) 简单线性回归1、lm(): (data是数据框) 例:fit - lm(weight height, data = women)summary(fit)women$weightfitted(fit)residuals(fit)plot(women$height, women$weight, main = Women Age 30-39, xlab = Height (in inches), ylab = Weight (in pounds)多项式回归例:fit2 - lm(weight height + I(height2), data = women)summary(fit2)
copyright@ 2008-2022 冰豆网网站版权所有
经营许可证编号:鄂ICP备2022015515号-1