Sambuddha Chakraborty

BB JEff,
You raise 2 very vital issues:

Cost-Metric correlation problem
Complexity comparison
First, we often get into the trap of setting up metrics that are intuitive and easy to measure. We do in in the spirit of implementing measurables for our business & processes, whether or not a change in the metric translates into a change in cost…[Read more]

As far as I know, Bill Smith, an engineer in Motorola was the person who came up with this idea. Little did he know that he was onto something this big.
Another name worth mentioning is Reigle Stewart, my mentor in Statistical Tolerancing which is an integral part of Six Sigma (DFSS). He, along with Mikel Harry, wrote the first manual on the…[Read more]

Mr. Hammer,
Clearly, in your experience, sir,  you have seen quality initiatives to either fail, or not live upto their expectations.
But why blame the program for the failure of the initiatives? It could be because it took people a lot of time and resource to understand how to implement Six Sigma in the proper way – whether it is a small…[Read more]

Poornima,
I can see why you asked the question. And I feel,  the answer is hidden in your question. The success of Six-Sigma (call it by another name if you want) as a bottom-line oriented business model is very much a function of how a company approaches the deployment of the strategy accross its operations.
Thus, to Jina’s point, if a company…[Read more]

I agree with Joe, that 3.4 ppm is valid for “Motorola-like” processes or what some of the offshoots from Motorola would like to call as “industry average” observed.

But I feel lot of the people who practice 6-sigma don’t know where the 3.4 ppm comes from.

GE India trains their own people. That much I know.

I had been having the same question as you have i.e is there someone imparting training there in India?

If you get to know something, would you please let me know? I might know a group here in US, who might be interested in offering a certification course.

For a Standard Normal distribution, where the transformation is
Z=(x-mu)/sigma,
the transformed mean is 0, and standard deviation is 1.

It will not change no matter what your starting Normal distribution looks like.

P-value is calculated based on the value of a test statistic.

Depending on whether you have continuous or discrete variables as inputs and outputs, you set out to test different “null” hypotheses using different tests.

Each test tailor-made for certain types of problems, compares the data with a reference distribution e.g. t-distributon,…[Read more]