Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
2099017 | Trends in Food Science & Technology | 2011 | 9 Pages |
Abstract
The number of consumer complaints at a given time depends on the number of the product units sold and a set of probabilities such as that a unit is spoiled, opened by the consumer and complained about, none known exactly. The 'Expanded Fermi Solution' was originally developed for risk assessment based on such factors' assumed ranges. But it can be used to estimate the number of spoiled units in existence, or the probability of a complaint, from the number of actually received complaints, or to estimate the expected number of complaints from the other factors' ranges. The calculations are done by three free Wolfram Demonstrations using Monte Carlo simulations, and analytically for mutual verification. They are based on that according the Central Limit Theorem, estimates derived from the products of a set of factors varying randomly within their respective ranges have approximately lognormal distribution whose mode can be considered the Best Estimate.
Related Topics
Life Sciences
Agricultural and Biological Sciences
Food Science
Authors
Micha Peleg, Mark D. Normand, Maria G. Corradini,