From: Larry D'Agostino
Date: 22 May 2000
Time: 12:14:19
In your tutorial you mention, "Define homogeneous lots of product items. Use your knowledge of the patterns of the process to group the items into "natural lots". Lots based on purchase order alone must be subdivided into such natural lots for accurate acceptance decisions."
I have also noticed that you referenced Duncan's "Quality Control and Industrial Statistics". In this text (5th ed., p. 181) "Several principles should be followed in forming lots. First, if a lot a lot is homogenous, the larger it is the better. For large lots allow large samples at low unit cost, and large samples give good OC curves."
My question is why is this so vague? I know there are a lot of possibilities to run a sample plan but maybe this could be a little more coherent. It is my understanding that when a sample plan is formed you have criteria that establishes "n" samples to be taken from a lot of "N". Since "N" is drawn at random from a theoretical infinite process and "n" is a random sample of "N" then you have in fact a random sample "n" from the process.
Further, does this mean that it does not matter the value of "N". Can "N" be variable. If so, than what is to keep from using lots based on purchase order alone? I could use your help.