Talk:Taguchi methods
From Wikipedia, the free encyclopedia
 |
This article is within the scope of WikiProject Systems, which collaborates on articles about the idea of systems. If you would like to help, you can edit this article or visit the project page, where you can join the project and/or contribute to the discussion. | |
| Start | This article has been rated as Start-Class on the assessment scale. | |
| Mid | This article is on a subject of mid importance within Systems. | |
|
This article has been rated but has no comments. If appropriate, please review the article and leave comments here to identify the strengths and weaknesses of the article and what work it will need. |
||
There was a comment: There is a theorem I think - help appreciated immediately after the sentence
-
- The squared-error loss function had been used by John von Neumann and Oskar Morgenstern in the 1930s.
I have removed this, as it is conversational and not part of the article's substantive material.
-- JordanSamuels 13:57, 1 September 2006 (UTC)
I have added 'citation needed' to introduction, as there is nothing in the article that is critical of Taguchi methods or why it is controversial
-- stonemaccas
A lot of marketing companies say the use the "Taguchi method" in order to calculate their results for multivariant testing. There doesn't seem to be any mention of how they do this at all in this articule or what that calcuation consists of.
-- Paullb 01:59, 31 January 2007 (UTC)
[edit] Spam links
Could someone please check the external links? I was patrolling with Vandal proof and its possible that the last edit prior to my dated signature is a spam link to an advertising / commercial website. I don't know enough about this subject to tell. Thanks. Richard Harvey 06:43, 11 November 2006 (UTC)
[edit] Poorly written acticle
This acticle is poorly done and needs a lot of improvement. It appears to be written by people who don't understand the Taguchi Methods, and cannot even clearly explain the fundamental principles. It pays too much attention discussing whether Western statisticians endorse the Taguchi Methods, and does not reference the many successful examples of its implementation in the engineering world.
A part of the introduction should say something like "Taguchi Methods are used in product development to make a design robust, ie. noise factors (factors that cannot be controlled, such as ambient temperature) have negligible effect on the function of the product.
I have a lot of experience in using Taguchi myself and can attest to its usefulness. I have generally found that people who criticize Taguchi either don't understand it at all, or have incorrectly used it and thus had an unsuccessful outcome.
I suggest that the book "Engineering Methods for Robust Product Design" by Fowlkes and Creveling be added to the list of references. Also, add this as an external link -http://www.isixsigma.com/library/content/c020311a.asp Logicman1966 03:46, 26 July 2007 (UTC)
[edit] Needs work
I agree that this page needs work (although I don't agree regarding the usefulness of the Taguchi method, I'm sceptical to most statistical methods and think they are usually better to replace by common sense). I was forced to use Taguchi at work and didn't get any valuable help at Wikipedia for once. The following pages contain interesting info: http://www.ee.iitb.ac.in/~apte/CV_PRA_TAGUCHI_INTRO.htm http://www.itl.nist.gov/div898/handbook/pri/section5/pri56.htm http://best.me.berkeley.edu/~aagogino/me290p/f98/slides/Taguchi/airplane.html http://www.isixsigma.com/library/content/c020311a.asp
I'd escpecially like to see some focus on how the so-called othogonal arrays (which basically are just arrays of tests all of which should be independant of eachother) are used etc. The information in Wikipedia is too general, and most examples I found at other pages (isixsigma for instance) are illustrative but don't help at all in understanding the details of the analyses.
Sorry I'm only able to point out the weaknesses, hope someone else will find interest to update this page. Even though I don't like the method, it would be useful to get help in understanding it from Wikipedia, so that I can argue more efficiently why I don't like it..
