Hi! I came accross this statistics issue and am hoping to get some suggestions from here. As part of our experiment design we have a need to statistically quantify the number of bacteria in a bag of medium. The goal is to be able to say that the bag is bacteria-free after evaluating some sampels taken from the bag. The size of the total medium is 50 ml for the bag and the volume of sample taken for evaluation is 0.5 ml.
My first thought is to divide the bag into 100 units of 0.5 ml. For each sample, it's either bacteria-positive or bacteria-negative. From there, if I use a bionomial approach to test bwteen 1% and 40% bacteria+ by approximating wth normal distribution, I come up with n=5 (sample size) for 0.05 level of significance and 95% power. The issue is that since it's small sample size with small porpotion (that is np<5), I don't know if using normal distribution approximation is justified. For pratical reason, a large sample size >10 is usually not attainable. Any other thoughts, for example, not to use bionomial approach, or to set any criteria for quantifying the number of bacteria in a bag (50ml) by sampling (0.5 ml each) is highly welcome! Thank you for any advice! . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
