Probability is a key factor in acceptance sampling, but it is not the only factor. If a company makes a million products and tests 10 units with one default, an assumption would be made on probability that 100,000 of the 1,000,000 are defective. However, this could be a grossly inaccurate representation. More reliable conclusions can be made by increasing the batch size higher than 10, and increasing the sample size by doing more than just one test and averaging the results. When done correctly, acceptance sampling is a very effective tool in quality control.

Source: www.investopedia.com