Calculating six sigma?
Six Sigma – iSixSigma › Forums › Old Forums › General › Calculating six sigma?
- This topic has 4 replies, 4 voices, and was last updated 17 years, 5 months ago by
Joe Gendron.
-
AuthorPosts
-
November 21, 2002 at 4:02 pm #30849
I am developing a web based reporting tool. One of the reports it needs to include is a 6 sigma report.
I am having incredible trouble trying to find a way to convert DPMO into a sigma level. In Excel one would use the ‘NORMSINV’ function but this isn’t avaible in VBScript/ASP.
Has anyone experienced and solved the same problem? Does anyone know of a way to replicate the ‘NORMSINV’ function, maybe the actual formula behind it?
I’m really stumped on this one so any help would be greatly appreciated!0November 21, 2002 at 4:12 pm #80933Ben,
Microsoft has a knowledge base article available that discusses the Normsinv function included within Excel. It contains the formula that they use — I’m sure it will help move you in the right direction:
http://support.microsoft.com/default.aspx?scid=KB;en-us;q87866
Good luck.
Mike0November 21, 2002 at 4:26 pm #80936If all else fails. one sigma = R Bar / d2
0November 21, 2002 at 6:04 pm #80942Having followed Mike’s lead (thanks Mike) I have obtained the following:
The NORMSINV function returns the inverse of the standard normal cumulative distribution function for a particular probability. In other words, given a probability, p, the NORMSINV function returns the value, x, of the normally distributed random variable, Z(0,1), which attains that probability. The Excel function adheres to the following mathematical approximation, x(p), of the inverse of the standard normal CDF:
x(p) = t – (c0+c1*t+c2*t^2)/(1+d1*t+d2*t^2+d3*t^3) + error(p) where: t = sqrt(ln(1/p^2))c0 = 2.515517c1 = 0.802853c2 = 0.10328d1 = 1.432788d2 = 0.1889269d3 = 0.001308
With these parameters, abs(error(p))<4.5*10^-4.
It does not however return the same value as NORMSINV. There is no obvious correlation between the result of this formula and the output of NORMSINV!!I am tantilisingly close now so if you know the reason why, please let me know!0December 16, 2004 at 8:54 pm #112542
Joe GendronParticipant@Joe-GendronInclude @Joe-Gendron in your post and this person will
be notified via email.See if this helps, worked for me.
http://www.source-code.biz/snippets/vbasic/9.htm0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.