Text Size


http:// http://money.howstuffworks.com/six-sigma4.htmThanks Nick. Very interesting important perspective.

On May 29, 2012, at 12:33 AM, nick herbert wrote:


I hate Facebook so I am sending this via eMail:

"Absolute effect size is larger in parapsy than in many famous physics experiments, but signal to noise and reproducibility

are much worse than in physics."   

"Case in point is the present state of the Higgs boson which is at the parapsychology level of discovery. That is Atlas has seen a few  (possible) Higgs event a few sigma above background and CMS has seen a few (possible) Higgs events
at 1.5 sigma above background. But the threshold for announcing DISCOVERY is 5 sigma.

[There is no parapsychology experiment that ever reaches 5 sigma but the Dean Device is doing 3 sigma, which is comparable to the S/N of the (alleged) Higgs signal after a year of LHC running.]

LHC is back on line at higher luminosity and most physicists expect/hope that the Higgs signal will exceed the 5 sigma threshold sometime this year.

But what is the absolute effect size of these Higgs events? Very Very Very small.

Many trillions of protons collide but only a few thousand of them react, of these that do, only a few reactions create a higgs boson. And of those Higgs's only a very few decay into the di-photon channel that makes them stand out from the background.

So we are talking about colliding trillions of protons to get just a handful of visible Higgs's.

That's an awful small effect size.

If Radin's effect size is 1%--that's one in a hundred  not one in a hundred trillion like the Higgs signal at LHC."

end of Nick Herbert's commentary.

"So, when people in Six Sigma talk about the "sigma of a process," what they're really referring to is the Z score. But the key point is this: You can improve the quality of a process by reducing variation. Your goal is Six Sigma quality, which is an attempt at perfection, or reducing variation to less than four defects per million opportunities measured."