help needed to create a dataset, thanks.

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Could anybody please help me to create a longitudinal concentration dataset including:

100 subjects (ID)
51% female (randomly assigned)
every subject has 3 study days (study day 1, study day 30 and study day 60)
ID from 1 to 50 was given 50mg dose and rest was given 150mg; value of 50 and 150 are under colume of dose

75% sparse data (group = 1) which means on each study day, time points are 0 and random number between 1 and 3 hours (total 2 time points)

25% rich data (group = 0)which means on each study day, time points are 0,1,2,3,4,5,6,8,10,24 hours (total 10 time points)

Appreciate for teaching.

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏1 回帖

关键词：dataset thanks Create NEEDED creat including subjects assigned

不知道有没有理解对你的意思

ID <- 1:100
sex <- rep("Male", 100)
sex[sample(1:100, 51)] <- "Female"
ID <- rep(ID, each = 3)
sex <- rep(sex, each = 3)
day <- rep(c(1, 30, 60), times=100)
dose <- rep(50, 300)
dose[ID>50] <- 150

data1 <- data.frame(ID, sex, day, dose)

sparseid <- sample(1:100, 75)
sparsetime1 <- cbind(sparseid, rep(0, 75))
sparsetime2 <- cbind(sparseid, sample(1:3, 75, replace=T))
sparsetime <- rbind(sparsetime1, sparsetime2)
sparsetime <- sparsetime[order(sparsetime[, 1]), ]

richid <- rep(setdiff(1:100, sparseid), each=10)
richtime <- rep(c(0,1,2,3,4,5,6,8,10,24), 25)
richtime <- cbind(richid, richtime)

times <- rbind(sparsetime, richtime)
times <- times[order(times[, 1]), ]

data2 <- data.frame(ID = rep(times[, 1], each=3), time = rep(times[, 2], each=3), day = rep(c(1, 30, 60), times=nrow(times)))

data <- merge(data1, data2, all=T, sort=T)

data <- data[order(data$ID, data$day, data$time), ]

Thank you very much! it is really helpful! Thanks again!