Question

I’m trying to create a table of quantiles in R for multiple subsets of data.

Right now, I have a vector of ids (p_ids) in table DATA, which are not consecutive. For each value in p_ids, I am looking to list the quantiles.

So far, I’ve tried variations of:

i <- 1
n <- 1

for (i in p_ids) {
    while(n <= nrow(data)) {
        quantiles[n] <- quantile(subset(alldata$variableA, alldata$variableB == i),
                                 probs = c(0,1,2,3)/3)
        n <- n + 1
    }
}

I know my issue lies somewhere in the index, but I can’t seem to get where the index should go. Suggestions?

Answer 1

You should look into using aggregate to do your quantiles for you
http://stat.ethz.ch/R-manual/R-devel/library/stats/html/aggregate.html

setting FUN=quantiles and by=p_ids should do what you want.

That is unless I’ve misunderstood your question.