您可以只创建一个变量而不是三个。我在用ddply
来自 plyr 包
那。
mydata<-structure(list(ID = c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L), NP = c(11L, 11L, 11L, 12L, 12L, 12L, 21L, 21L, 21L,
22L, 22L, 22L), Time = c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L), Outcome = c(4L, 3L, NA, 2L, 3L, 3L, 2L, NA, NA,
4L, 4L, 4L)), .Names = c("ID", "NP", "Time", "Outcome"), class = "data.frame", row.names = c(NA,
-12L))
library(plyr)
mydata1<-ddply(mydata,.(ID,Time),transform, NP.T=length(Outcome[which(Outcome !="NA")]))
>mydata1
ID NP Time Outcome NP.T
1 1 11 1 4 2
2 1 12 1 2 2
3 1 11 2 3 2
4 1 12 2 3 2
5 1 11 3 NA 1
6 1 12 3 3 1
7 2 21 1 2 2
8 2 22 1 4 2
9 2 21 2 NA 1
10 2 22 2 4 1
11 2 21 3 NA 1
12 2 22 3 4 1
Updated: 也可以用interaction
创建结合 ID 和时间的唯一变量(梳)
mydata1<-ddply(mydata,.(ID,Time),transform, NP.T=length(Outcome[which(Outcome !="NA")]),comb=interaction(ID,Time))