library(ISwR)
attach(juul)
4.3分组数据的汇总统计量
attach(red.cell.folate)
tapply(folate,ventilation,mean)#提取folate变量，根据ventilation分组，然后对每一组计算均值
N2O+O2,24h N2O+O2,op O2,24h
316.6250 256.4444 278.0000
tapply(folate,ventilation,sd)#标准差
N2O+O2,24h N2O+O2,op O2,24h
58.71709 37.12180 33.75648
tapply(folate,ventilation,length)#长度
N2O+O2,24h N2O+O2,op O2,24h
8 9 5
#较好的显示代码
xbar<-tapply(folate,ventilation,mean)
s<-tapply(folate,ventilation,sd)
n<-tapply(folate,ventilation,length)
cbind(mean=xbar,std.dev=s,n=n)#按列将均值，标准差，长度向量合在一起
mean std.dev nN2O+O2,24h 316.6250 58.71709 8
N2O+O2,op 256.4444 37.12180 9
O2,24h 278.0000 33.75648 5
#缺失值问题
tapply(igf1,tanner,mean)#
I II III IV V
NA NA NA NA NA
tapply(igf1,tanner,mean,na.rm=T)#通过添加参数na.rm=T来处理缺失值问题
I II III IV V
207.4727 352.6714 483.2222 513.0172 465.3344
aggregate(juul[c("age","igf1")],
list(sex=juul$sex),mean,na.rm=T)#对整个数据框操作，并且把结果作为一个数据框显示
sex age igf1
1 M 15.38436 310.8866
2 F 14.84363 368.1006
aggregate(juul[c("age","igf1")],juul["sex"],mean,na.rm=T)#将数据框juul中变量age，igf1数据按sex分类计算均值，结果作为数据框显示
sex age igf1
1 M 15.38436 310.8866
2 F 14.84363 368.1006
by(juul,juul["sex"],summary)#by处理整个数据框，按sex分类总结juul数据
sex: M
age menarche sex igf1 tanner
Min. : 0.17 No : 0 M:621 Min. : 29.0 I :291
1st Qu.: 8.85 Yes : 0 F: 0 1st Qu.:176.0 II : 55
Median :12.38 NA’s:621 Median :280.0 III : 34
Mean :15.38 Mean :310.9 IV : 41
3rd Qu.:16.77 3rd Qu.:430.2 V :124
Max. :83.00 Max. :915.0 NA’s: 76
NA’s :145
testvol
Min. : 1.000
1st Qu.: 1.000
Median : 3.000
Mean : 7.896
3rd Qu.:15.000
Max. :30.000
NA’s :141
sex: F
age menarche sex igf1 tanner
Min. : 0.25 No :369 M: 0 Min. : 25.0 I :224
1st Qu.: 9.30 Yes :335 F:713 1st Qu.:233.0 II : 48
Median :12.80 NA’s: 9 Median :352.0 III : 38
Mean :14.84 Mean :368.1 IV : 40
3rd Qu.:16.93 3rd Qu.:483.0 V :204
Max. :75.12 Max. :914.0 NA’s:159
NA’s :176
testvol
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA’s :713