[R] single-pass algorithm for quantile calculation

Duncan Murdoch murdoch at stats.uwo.ca
Tue Apr 3 21:41:10 CEST 2001


On Tue, 3 Apr 2001 13:31:32 -0500 , you wrote in message
<AFD78192EC49D311BFAE00902798AB8F0BDEA0 at jupiter.sc.arbitrade.com>:

>Dear R users, I am looking for a reference to an algorithm for estimation of
>sample quantiles which does not require bringing the whole data into memory
>(more precisely its memory complexity should be much less than linear,
>ideally constant). I realize that such an algorithm can only be approximate
>and actually quite wrong for some samples, but that's fine with me.

What about a single pass SRS algorithm to get a fixed size subsample,
then approximate the quantiles of the real sample with the quantiles
of the subsample?

Duncan Murdoch
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._



More information about the R-help mailing list