FOLLOWING POST PASTED FROM YAHOO GROUPS

ORIGINATOR: Ravi Sankar

DATE: Wed Jan 21, 2009

Greetings,

I have a question regarding sigma level calculation. 3.4 DPMO is associated with 4.5 sigma long term and why in this case the probability of good products is considered from -infinity to +Zlt and not from -Zlt to +Zlt.

Regards

_______________

FOLLOWING REPLY WAS RECEIVED

Dear All,

Ravi has raised an important point. If you refer to the figure below, you can see that it shows a shift of 1.5 s. You can also notice that the yellow area corresponds to 3.4 defects per million in a six sigma process. Important thing to note here is that we consider defects only on one side and not on the other side (correctly pointed out by Ravi.)

The reason for this is that at any given point in time shift can happen only to the right of the target or to the left of the target. This means the number of defects are either zero (negligible) on the left and 3.4 dpm on the right or 3.4 dpm on the left side and zero (negligible) on the right side. When we consider shift, defects are not equally distributed on both sides.

So for a Six Sigma shifted situation, the defects are not 3.4 defects per million on each side, but 3.4 dpm on one side (this could be left or right side of target) .

I hope this clarifies.

VK

yes, thanks.

Thanks Vk, Even i was having the same question on mind, But the given example was really great to understand.

Thanks

Devi