R语言统计入门第四章描述性统计和图形——4.1单组的汇总统计量

4.1单组汇总统计量

x<-rnorm(50)
mean(x)#均值

[1] 0.152391

sd(x)#标准差

[1] 0.9543512

var(x)#方差

[1] 0.9107863

median(x)#中位数

[1] 0.2121978

quantile(x)#四分位数

0% 25% 50% 75% 100%
-2.0704040 -0.5317435 0.2121978 0.8127855 2.4617495

pvec<-seq(0,1,.1)
pvec

[1] 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0

quantile(x,pvec)#十分位数

0% 10% 20% 30% 40% 50%
-2.07040404 -1.07545354 -0.79550026 -0.27400948 0.00690431 0.21219785
60% 70% 80% 90% 100%
0.42431976 0.62543867 1.00878549 1.22029739 2.46174948

attach(juul)#将数据框置于系统搜索路径
mean(igf1)#R无法跳过缺失值，

[1] NA

mean(igf1,na.rm = T)#na.rm=T参数跳过缺失值

[1] 340.168

sum(!is.na(igf1))#计算观测值个数

[1] 1018

summary(juul)#对数值变量进行汇总

age menarche sex igf1
Min. : 0.170 Min. :1.000 Min. :1.000 Min. : 25.0
1st Qu.: 9.053 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:202.2
Median :12.560 Median :1.000 Median :2.000 Median :313.5
Mean :15.095 Mean :1.476 Mean :1.534 Mean :340.2
3rd Qu.:16.855 3rd Qu.:2.000 3rd Qu.:2.000 3rd Qu.:462.8
Max. :83.000 Max. :2.000 Max. :2.000 Max. :915.0
NA’s :5 NA’s :635 NA’s :5 NA’s :321
tanner testvol
Min. :1.00 Min. : 1.000
1st Qu.:1.00 1st Qu.: 1.000
Median :2.00 Median : 3.000
Mean :2.64 Mean : 7.896
3rd Qu.:5.00 3rd Qu.:15.000
Max. :5.00 Max. :30.000
NA’s :240 NA’s :859

detach(juul)#将路径上的数据框移除

library(ISwR)
juul$sex<-factor(juul$sex,labels=c("M","F"))#创建水平因子,附加标签M，F
juul$menarche<-factor(juul$menarche,labels = c("No","Yes"))
juul$tanner<-factor(juul$tanner,
                    labels = c("I","II","III","IV","V"))
attach(juul)
summary(juul)#对整个数据框进行汇总

age menarche sex igf1 tanner
Min. : 0.170 No :369 M :621 Min. : 25.0 I :515
1st Qu.: 9.053 Yes :335 F :713 1st Qu.:202.2 II :103
Median :12.560 NA’s:635 NA’s: 5 Median :313.5 III : 72
Mean :15.095 Mean :340.2 IV : 81
3rd Qu.:16.855 3rd Qu.:462.8 V :328
Max. :83.000 Max. :915.0 NA’s:240
NA’s :5 NA’s :321
testvol
Min. : 1.000
1st Qu.: 1.000
Median : 3.000
Mean : 7.896
3rd Qu.:15.000
Max. :30.000
NA’s :859

juul<-transform(juul,
                sex=factor(sex,labels = c("M","F")),
                menarche=factor(menarche,labels = c("No","Yes")),
                tanner=factor(tanner,labels = c("I","II","III","IV","V")))