A New Method for Marketing Research and Product Development Based on Choice Modeling and Weighted Regression

For consumer protection, many governments perform random inspections on goods sold by weight or volume to ensure consistency between actual and labeled net contents. To pass inspection, samples must jointly comply with restrictions placed on the individual sampled items and on average. In this talk the current US National Institute of Standards and Technology joint acceptance criteria is used. Motivated by a problem from a real manufacturing process, an approximation for the probability of sample acceptance is proposed that is applicable for processes with one or more known sources of variation. This approach also allows the assessment of the importance of the sampling scheme of the items.