Valid study for CO samples both Analyzer and Drager Tube results?



I am trying to set up a valid study of Carbon Monoxide readings in Liquid Product. Presently, at our more modern plants, we sample the Batches continuously by analyzer and I have available a data sample for each batch (automatically logged). The Lots are sampled Prior to loading and at load finish. Sometimes by analyzer (if available) and at other facilities by Drager tube. My problem has been that when I try for a high confidence level the sample size ends up above 40,000. (far too many for us to manually log) Possibly I am attempting for too high of a level. We would like to end up reducing our sampling, after we prove that the system is under control; to once each batch and set up a random sample plan to ensure the lots remain under control. Thank-you in advance

Don Winton

What confidence level are you trying to achieve?

This site <A HREF="" TARGET="_blank"></A> has some good stuff on sampling.

This site <A HREF="" TARGET="_blank"></A> has some standards for download that may be of use.



I was better but I got over it.
Top Bottom