Hi all, I just need help understanding the filter function. I've seen how to use it to smooth a time series, but how do you know which is a good smoothing? Also, I have seen people do things like x1 = filter(x,filter=rep(1/5,5)) or x2 = filter(x,filter=rep(1/10,10)). I know that rep creates a vector with the first argument repeated the number of times in the second argument (e.g 1/5 1/5 1/5 1/5 1/5). But how does this have anything to do with the filter? Is the filter function some sort of unexplained algorithm? I just don't understand how it works. Thanks. -- View this message in context: http://www.nabble.com/filter-function-for-time-series-tp24852699p24852699.html Sent from the R help mailing list archive at Nabble.com.