There is quite a literature on related methods for variance. If anyone is interested, I did some work (and even published the code in the magazine Interface Age in 1981) on some of these. I could probably put together scans of relevant materials, some of which are not easily available. It would make a good Master's or senior undergrad project, and could be (possibly has been) extended to compute covariance matrices properly for very large data sets and streaming data. JN
On 13-07-27 06:00 AM, r-devel-request at r-project.org wrote:
Message: 6 Date: Fri, 26 Jul 2013 12:58:28 +0000 From: Ravi Varadhan<ravi.varadhan at jhu.edu> To: Joshua Ulrich<josh.m.ulrich at gmail.com>, Zach Harrington <zach.harrington at gmail.com> Cc:"r-devel at r-project.org List" <r-devel at r-project.org> Subject: Re: [Rd] What algorithm is R using to calculate mean? Message-ID: <2F9EA67EF9AE1C48A147CB41BE2E15C3491530 at DOM-EB-MAIL1.win.ad.jhu.edu> Content-Type: text/plain; charset="us-ascii" This uses the idea of Kahan's summation, if I am not mistaken. http://en.wikipedia.org/wiki/Kahan_summation_algorithm Ravi
__________________________