Variation

I have a question for the bright minds who read this forum:Formed parts are made, 20 at a time from a die that forms a compound into disks. These disks are then fed to another piece of equipment that processes the part into the next step.Variation may occur across the disk and out of spec thickness at any spot can cause a shutdown at the next station. QA people normally measure the disk in 12 spots around the perimeter and toward the center of the disk because of the nature of the compound and the “grain” orientation.The question of sample size came up and someone suggested that we would need Five (5) samples. If we assume five per cavity, then we realistically have a total sample size of 1,200 when we consider the total measurements.An alternative was suggested: we consider each measured spot on a disk as a sample (therefore 12 samples per disk). A single forming operation would provide 20 disks, and therefore a total sample size of 240.This will provide insight into variation within the die and within each disk. It will not provide information regarding variation within a cavity.Because the experts in the process expect that little variation exists from disk to disk (within the same forming cavity) outside of special causes, this may be the best way to go initially.Any thoughts would be appreciated.