Comments on: Theoretical explanation for numerical results

By: Welford’s method for calculating the sample variance: An implementation in Scheme | Left Censored

Sat, 17 Dec 2011 16:44:27 +0000

[...] definitions. He provides a Monte Carlo comparison of methods here, and a theoretical discussion here. He has also provides a C++ implementation of Welford’s method [...]

By: Running Variance | TaylorTree

Running Variance | TaylorTree — Thu, 16 Dec 2010 03:06:47 +0000

[...] Theoretical explanation for numerical results [...]

By: Diana

Diana — Mon, 05 Jul 2010 03:24:46 +0000

“I don’t know”

By: Diana

Diana — Mon, 05 Jul 2010 03:23:50 +0000

Thank you again! I don’t why I didn’t see it before :O

By: John

John — Sun, 04 Jul 2010 19:59:58 +0000

Diana: Please see the references at the bottom of this page.

By: Diana

Diana — Sun, 04 Jul 2010 19:32:54 +0000

While working on my undergraduate thesis, I had to choose a convenient way to calculate variance using a DSP (for finding the power of two signals). That’s how I came across your blog and I decided to implement my design using the methods of: direct formula method and Welford’s method having satisfactory results with both of them, but overall preferring the Welford’s method.
In the book of my thesis I mentioned the disadvantages that you pointed out about the sum of squares formula, but now I’m being asked for a more formal bibliographical source (I put a link to this blog entry) or for an statistical study. I appreciate if you could tell me how to find any of those sources because if I can’t give those references I’ll have to remove the whole topic of the selection of the variance method, and I wouldn’t like that because I think it was very relevant in the design.
Thank you so much for your help

By: Walking Randomly » Fun with linspace and the colon operator in MATLAB

Walking Randomly » Fun with linspace and the colon operator in MATLAB — Fri, 13 Mar 2009 12:10:56 +0000

[...] things like the order of operations matters. This sort of thing has been discussed many times by people considerably more erudite than me so I refer you to them for [...]