Quantitative Risk Assessment Methods: Probabilistic Methods

This course is a hands-on introduction to Quantitative Methods for Food Safety Risk Analysis.  Quantitative methods use available data to describe (model) what is observed. These models have many uses. They are used to help explain observations, to make predictions about future events, or to provide decision-makers with tools to test the impact of alternative solutions to problems.  Analysis of a particular risk may require a series of models to describe various components, or steps, that impact on the risk. Typically, we call such a series of models a Quantitative Risk Assessment.

Quantitative risk assessment and quantitative methods generally can be very powerful, but require a strong command of the science and art of probabilistic methods. The results of a model can be very sensitive, for example, to the choice of distributions.  Using the wrong assumptions in a model can produce incorrect results. Incorrect results can lead to poor decisions, and to undesirable outcomes.

Quantitative methods are extremely useful tools.  This short course trains aspiring and experienced modelers in the use of probabilistic methods. The course uses @Risk™ software as the primary tool for advancing the student’s knowledge.  Successful participants will emerge from this course with basic @Risk™ skills and be prepared to advance into the Quantitative Methods: Model Building course.  @Risk™ software is provided to students for use in the course.  @Risk™ builds upon an intermediate knowledge of Microsoft Excel™ or other spreadsheet software.  Training in Excel™ is not provided by the JIFSAN program.

The course is conducted in a computer teaching laboratory. Lectures describe various techniques.  Students then work individually or in groups to solidify their understanding of the lecture materials, and to begin to build quantitative skills.

Overview of Topics

Learning Objectives

After completing this course, students understand:

• Where probabilities come from
• Basic laws of probability and how to express it
• Differences between discrete and continuous random variables
• The importance of probability distributions in risk assessment
• The kinds of parameters required to define a distribution
• The most common discrete and continuous probability distributions
• The difference between an analytical solution and a simulation
• The two steps of the Monte Carlo process
• The differences between variability and uncertainty
• The reasons for separating uncertainty and variability
• The steps in a bootstrap procedure
• How to use @Risk™ software

View all courses