| SITE MAP | CONTACT US | LOCATIONS | HOME |
Links

 
      

Animal agriculture and food safety risk analysis

Duration: 2 weeks

Course overview

The course is split into two self-contained modules. The course has been significantly revised, particularly in Module 2 to include our research on model frameworks and model validation.

Module 1 lasts five days and provides the basic principles of risk assessment and where it fits in to the risk analysis process. It also looks at resource, strategy and communication issues that management face in risk assessment. It covers some basic modeling principles, and gets the participants used to the risk analysis modeling environment (in this case Crystal Ball with Excel or @RISK with Excel, but the lessons apply equally well to other modeling environments). We also look at essential probability and statistics theory and various stochastic processes. This module covers material that is essential for Module 2.

Module 1 will be useful for analysts starting out in animal health, microbial, antimicrobial or toxicological food safety risk assessment who have some basic knowledge of simulation modeling and to risk managers in general. This is a key module that should be taken before attending Module 2.

Module 2 also lasts five days and has been greatly revised and should appeal to those who have already attended one of Vose Consulting's previous courses. The focus is less on the predictive microbiology and dose-response models, and more on producing models that risk managers can put their faith in. Thus, we introduce a framework for model construction that we developed for the USDA to help find the simplest model that will adequately solve the manager's problem. The framework offers a way to demonstrate consistency of approach despite some models appearing to be very different and addresses how to structure a model that makes the best use of available data. We will also introduce a method new to food safety for indicating to a risk manager whether, given the myriad assumptions and approximations, the quality of data and level of scientific knowledge of the issue, the quantitative risk analysis results are sufficiently robust to be relied upon.

Module 2 provides an in-depth knowledge of the modeling techniques necessary for international level risk assessments. We critically look at risk models, and the participants are encouraged to bring along modeling problems they are currently faced with. Attendance of Module 1 or prior knowledge of the material covered in Module 1 will be needed. If you are considering only attending Module 2, please run through the short self-test to make sure you have the knowledge provided in Module 1.

This module is suited to those already familiar with spreadsheets, who have some modeling experience and who are interested in developing these abilities further. The module content will enable the participants to produce realistic, professional quality models. It is designed to encourage the modeler to develop creative problem solving skills through plenty of problem exercises.

Please review the level of computer (Excel and Windows) knowledge necessary before attending the course. Participants should review this information well in advance. The requirements are very basic but ensuring that all participants arrive with this basic level prevents us from wasting too much time on familiarization with Excel rather than learning about risk modeling.

Further details on the modules are provided below.

top


Training material

All lecture notes are provided as PowerPoint files. A CD of these files is provided to each participant. Printed handouts are also provided. The CD also contains all model files produced for the course. Any extra models developed during the course are downloadable from a private page on this web site dedicated to the course.

top


Course format

The course runs from 09:00 to 17:00 each day. Morning and afternoon coffee, lunch and dinners (Tuesday, Thursday) are provided. Cocktails are offered on the Sunday from 18:00 to 20:00 before each module to meet your instructor and fellow participants.

top


Who should attend

Animal health, microbial, antimicrobial and toxicological food safety risk analysts and risk managers who have some basic knowledge of spreadsheets and simulation modelling. Statisticians and scientists providing input to a risk assessment.

top


Prerequisites

All models are developed using Excel and Crystal Ball or @RISK. It is essential that all participants are reasonably proficient in Excel (see prerequisites). Both courses are very intensive so, to save time, for @RISK users it is important to make themselves familiar with the basic principles of @RISK by going through the on-line tutorial. Crystal Ball users can take the Crystal ball on-line tutorial that is available here.

Participants are required to bring laptops loaded with Microsoft Word, Microsoft PowerPoint and Microsoft Excel and Decisioneering's Crystal Ball 7 or Palisade's @RISK 4.5 Professional installed, and with a CD drive. Trial copies of Crystal Ball and @RISK are available free of charge from Decisioneering and Palisade web-sites but these should not be installed too early as trial versions run out after 7 days for Crystal Ball and 10 days for @RISK. We can arrange copies of @RISK at a 20% discount should you wish to purchase.

Participants intending to take Module 2 only should ensure that they have already taken a course equivalent to Module 1 or possess the equivalent knowledge. Booking preference is given to people taking both modules.

top


Free ModelAssist

ModelAssist from Vose Consulting is a comprehensive risk analysis training and reference software tool. ModelAssist provides an in-depth explanation of all of the risk analysis concepts, techniques and methods introduced in this course and greatly complements the course material. It is particularly helpful as a reference for participants of the material that has been presented during the course.

top


Teaching philosophy

All of Vose Consulting's courses aim to help the participants understand (rather than 'learn') risk analysis, which can only be achieved through a relaxed, informal and interactive environment, through plenty of examples and hands-on exercises where students apply and adapt what they have learned.

top


Social events

Part of the value of specialist courses like these is the contacts one makes with others in the same field. It is quite a long course, and we'll need a break from time to time. The entertainment we provide is an excellent opportunity to relax, have some fun, build a rapport with other participants, establish some contacts and sample some of the local culture.

We therefore arrange optional fun, interactive social events which take advantage of local attractions, cuisine and culture. All social events are included in the course fee.

top


Course content by module

MODULE 1: INTRODUCTION TO RISK ANALYSIS, SOFTWARE, STOCHASTIC PROCESSES AND THEIR MODELLING

Day 1

  • Introduction to risk analysis
    • The partition of risk assessment and risk analysis in the management of risk
    • Establishing a risk policy
    • The roles of risk managers and risk assessors
    • Risk communication
  • Introduction to risk assessment:
    • Moving from an intellectual exercise to a useful decision tool
    • Identification of a risk
    • Establishing risk assessment objectives
    • Creating and managing a risk assessment team
  • Difficulties in modelling biological systems

Day 2

  • Introduction to risk analysis modelling methods
    • Monte Carlo simulation, Crystal Ball or @RISK and Excel
    • Calculation vs. simulation
    • Uncertainty, variability and inter-individual variability
  • Typical modelling results, their presentation and interpretation
  • Introduction to descriptive statistics
    • Mean, standard deviation, skewness, kurtosis, percentiles
  • Introduction to probability theory
    • Probability concepts
    • Graphical representations of risk events: Venn diagrams, fault trees and event trees
    • Probability vs. population distributions, relative vs. cumulative, discrete vs. continuous

Day 3

  • Binomial Process
    • Binomial, beta, negative binomial and geometric distributions
  • Problems to solve
  • Nested binomials

Day 4

  • Poisson process
    • Poisson, gamma, m-Erlang and exponential distributions.
  • Mixed Poisson and binomial processes
  • Problems to solve
  • Renewal process and its modelling

Day 5

  • Hypergeometric process
    • Hypergeometric and inverse hypergeometric distributions
  • Problems to solve
  • Central Limit Theorem
    • Normal and lognormal distributions
  • Markov process

MODULE 2: ADVANCED RISK ANALYSIS MODELLING

Day 1

  • Predictive microbiology
  • Dose-response modelling
  • A new hierarchal framework for building risk analysis models
    • Establishing consistency between models and defending their theoretical basis
    • Making models more efficient and valid
    • Building self-updating predictive models with MCMC

Day 2

  • Reviewing published models within the new framework
    • Could the models be simplified?
    • How would simplification affect the results and assumptions?
  • Uncertainty and variability
    • Meaning of uncertainty and variability, the value of their distinction, modelling techniques
    • Examples of modelling problems where they are usefully separated
    • Structures of two-dimensional (second order) risk analysis models
  • Classical statistics
    • Estimation of population mean and standard deviation
    • Estimation of population prevalence and Poisson mean

Day 3

  • Bayes' Theorem
    • Theory and derivation
    • Construction and simulation solutions
    • WinBUGS modeling

Note: Bayesian methods of statistics is used here considerably as an intuitive means of helping participants understand the connection between data and knowledge

Day 4

  • The Bootstrap
    • Non-parametric and parametric Bootstrap techniques
    • Use of Jack-knife for gauging robustness
    • Applications and problems to solve
  • Analysing and using data:
    • Checking quality and appropriateness
    • How to accept and reject different data sets
    • Spotting the traps and filling the gaps in reported data
  • Determining distributions from data
    • Assessing validity of data
    • First order distribution fitting
      • Fitting to parametric and non-parametric distributions
      • MLE and goodness of fit statistics
      • Using linear solvers with gof statistics for best fit
    • Second order distribution fitting
    • Parametric and non-parametric distributions
    • Likelihood estimating, Bootstrapping, other methods
    • Problems to solve

top

Day 5

  • Presenting risk analysis quantitative results
    • Statistical and graphical outputs from a risk assessment
  • Report writing
  • A new method for validating models and their results
    • Reviewing assumptions, knowledge and data quality
    • Integrating the model's vulnerabilities into a validity score
    • Graphical representation of validity

top

      
 
Legal Notice | Return/Refund policy | Privacy statement | Delivery terms
©Copyright 1997-2008 Vose Consulting. All Rights Reserved.