As a beginner, I have some queries regarding Dodge-Romig AOQL Table as follows:
1. If the rejected lots are 100% inspected (normally), then what is the objective of selecting a sample size using Dodge-Romig AOQL table (because we already know about the lot)? I find that if I inspect each and every item of a (rejected) lot, then selecting a sample size using AOQL table makes no sense.
THE LOGIC AND RULE: The general rule: "If the lots contain no defective items, no lots will be rejected, and the amount of inspection per lot
will be the sample size n. If the items are all defective, every lot will be submitted to
100% inspection, and the amount of inspection per lot will be the lot size N. If the lot
quality is 0 < p < 1, the average amount of inspection per lot will vary between the
sample size n and the lot size N." See attached, chapter 2 (last 2 pages).
Assume that there is a lot size N; we take a sample size n from lot N. If the sample n reveals that there are defects, then all lots (i.e. all lot Ni: (N1, N2, ...,Nj) will be submitted to 100% inspection. This is to verify whether all lots have defect or was it that the first lot that we found defect came out of the blue. If all lot with 100% inspection are found similar defect, then reject the entire production batch.
MAKING SENSE: In order to first discover defect, we need sample size n taken from Lot N. Now there are samples size nk: (n1, n2, ..., nk) from many lots: Nj: (N1, N2, ...,Nj), if there is defect in this sample---then we have good reason to suspect that "other lots" also contain defects. So, this lot that we intend to reject must be submitted to 100% inspection and to be sure all other lots we must also inspect 100%---if they contain defect, then reject them all. This approach helps us to avoid "human error" in the first lot's sample. This method allows the inspector to intensifies the audit when a defect is found in sample1.
REFERENCE: See attached article. Cheers.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size