I had gone through a number of blogs and websites to find the most elegant way to solve this problem, but to no avail. The best solution I could find was at http://rprogramming.net/recode-data-in-r/, but I didn't like apply+function as it would be an overkill for medical personnel and researchers (of whom I deal with on daily basis) without programming basics. I need an extremely simple solution so that people won't shy away from R. I could not get the problem off my mind until I finally found a simple solution on my own :-) Here I share the codes:

library("car") # create a data frame data = read.table(header=T, text=" Q1 Q2 Q3 Q4 Q5 2 2 2 2 1 2 1 2 1 2 2 2 2 2 2 3 3 3 1 1 2 2 2 2 1 ") # Let say for Q1, Q3 and Q5, the correct option is 3, thus recoded as 1, the rest as 0 data.recode = data mat = as.matrix(data.recode[c(1,3,5)]) mat = recode(mat, "3=1; else=0") data.recode[c(1,3,5)] = as.data.frame(mat) # Let say for Q2 and Q4, the correct option is 2, thus recoded as 1, the rest as 0 mat = as.matrix(data.recode[c(2,4)]) mat = recode(mat, "2=1; else=0") data.recode[c(2,4)] = as.data.frame(mat) # Compare the original data with recoded ones data data.recodeOutputs:

> data Q1 Q2 Q3 Q4 Q5 1 2 2 2 2 1 2 2 1 2 1 2 3 2 2 2 2 2 4 3 3 3 1 1 5 2 2 2 2 1 > data.recode Q1 Q2 Q3 Q4 Q5 1 0 1 0 1 0 2 0 0 0 0 0 3 0 1 0 1 0 4 1 0 1 0 0 5 0 1 0 1 0