[Elicitation pour l’évaluation des risques microbiologiques dans les aliments : vers une approche probabiliste de l’outil Risk Ranger]
Ross et Sumner (2002) ont proposé un outil sous la forme d’une feuille de calcul Excel, Risk Ranger, pour une évaluation des risques simple et rapide des dangers microbiologiques dans les aliments. Il permet de comparer et classer les risques liés à certains aliments en identifiant les facteurs qui y contribuent le plus. La sortie de l’outil est un score unique calculé à partir de réponses à 11 questions. L’objectif de ce travail est de faire évoluer l’outil Risk Ranger vers une version probabiliste. Nous proposons une procédure d’élicitation de la variabilité à l’aide de deux quantiles de la distribution d’intérêt. De plus, un niveau d’incertitude est spécifié grâce au degré de confiance fourni par les experts sur ces quantiles. Le nouvel outil, également sous forme d’une feuille Excel, permet à l’expert de modifier de vérifier graphiquement presque instantanément les conséquences de ses réponses sur l’incertitude et la variabilité de la quantité d’intérêt pour mieux les ajuster à son expertise.
Ross and Sumner (2002) proposed a convenient tool, Risk Ranger, for early-stage risk assessment of microbial hazards in food systems. The authors describe the tool as being a simple way of comparing and classifying food-related risks and highlighting main factors that contribute to food safety. The output of the tool is a risk score based on answers to 11 questions. The objective of this work was to extend Risk Ranger towards a probabilistic version, distinguishing uncertainty and variability. For each question, we propose an elicitation procedure where the expert is asked for two quantiles to assess variability. Experts are also asked on their degree of confidence for the given quantiles to incorporate an uncertainty level. The new tool, also an Excel worksheet, allows the expert to check graphically, almost instantly, the uncertainty and variability of the variable of interest from the elicited quantiles and then to interactively modify them according to his/her view.
Mot clés : élicitation, appréciation des risques, variabilité, incertitude
@article{JSFS_2013__154_3_113_0, author = {Guillier, Laurent and Kabunda, Jean-Marc and Denis, Jean-Baptiste and Albert, Isabelle}, title = {Elicitation for food microbial risk assessment: a probabilistic approach extending {Risk} {Ranger} proposal}, journal = {Journal de la soci\'et\'e fran\c{c}aise de statistique}, pages = {113--123}, publisher = {Soci\'et\'e fran\c{c}aise de statistique}, volume = {154}, number = {3}, year = {2013}, language = {en}, url = {http://www.numdam.org/item/JSFS_2013__154_3_113_0/} }
TY - JOUR AU - Guillier, Laurent AU - Kabunda, Jean-Marc AU - Denis, Jean-Baptiste AU - Albert, Isabelle TI - Elicitation for food microbial risk assessment: a probabilistic approach extending Risk Ranger proposal JO - Journal de la société française de statistique PY - 2013 SP - 113 EP - 123 VL - 154 IS - 3 PB - Société française de statistique UR - http://www.numdam.org/item/JSFS_2013__154_3_113_0/ LA - en ID - JSFS_2013__154_3_113_0 ER -
%0 Journal Article %A Guillier, Laurent %A Kabunda, Jean-Marc %A Denis, Jean-Baptiste %A Albert, Isabelle %T Elicitation for food microbial risk assessment: a probabilistic approach extending Risk Ranger proposal %J Journal de la société française de statistique %D 2013 %P 113-123 %V 154 %N 3 %I Société française de statistique %U http://www.numdam.org/item/JSFS_2013__154_3_113_0/ %G en %F JSFS_2013__154_3_113_0
Guillier, Laurent; Kabunda, Jean-Marc; Denis, Jean-Baptiste; Albert, Isabelle. Elicitation for food microbial risk assessment: a probabilistic approach extending Risk Ranger proposal. Journal de la société française de statistique, Méthodes statistiques en agronomie, Tome 154 (2013) no. 3, pp. 113-123. http://www.numdam.org/item/JSFS_2013__154_3_113_0/
[1] Combining expert opinions in prior elicitation, Bayesian Analysis, Volume 7 (2012) no. 3, pp. 503-532 | MR | Zbl
[2] Fuzzy risk assessment tool for microbial hazards in food systems, Fuzzy Sets and Systems, Volume 157 (2006) no. 9, pp. 1201-1210 | MR
[3] A swift Quantitative Microbiological Risk Assessment (sQMRA) tool, Food Control, Volume 21 (2010) no. 3, pp. 319-330
[4] Foodborne zoonoses due to meat: a quantitative approach for a comparative risk assessment applied to pig slaughtering in Europe, Veterinary Research, Volume 39 (2008) | DOI
[5] A risk-based sampling plan for monitoring of histamine in fish products, Journal of Food Protection, Volume 74 (2011) no. 2, pp. 302-310
[6] Challenges of quantitative microbial risk assessment at EU level, Trends in Food Science and Technology, Volume 19 (2008) no. SUPPL. 1, p. S22-S29
[7] Risk profiles of pork and poultry meat and risk ratings of various pathogen/product combinations, International Journal of Food Microbiology, Volume 126 (2008) no. 1-2, pp. 1-12
[8] Evaluating variability and uncertainty separately in microbial quantitative risk assessment using two R packagess, International Journal of Food Microbiology, Volume 142 (2010), pp. 330-340
[9] A simple, spreadsheet-based, food safety risk assessment tool, International Journal of Food Microbiology, Volume 77 (2002) no. 1-2, pp. 39-53
[10] Risk evaluation and management to reaching a suggested FSO in a steam meal, Food Microbiology, Volume 28 (2011) no. 4, pp. 631-638
[11] A semi-quantitative seafood safety risk assessment, International Journal of Food Microbiology, Volume 77 (2002) no. 1-2, pp. 55-59
[12] A risk microbiological profile of the Australian red meat industry: Risk ratings of hazard-product pairings, International Journal of Food Microbiology, Volume 105 (2005) no. 2, pp. 221-232
[13] Solving for the parameters of a beta distribution under two quantile constraints, Journal of Statistical Computation and Simulation, Volume 67 (2000) no. 2, pp. 189-201 | Zbl