Dr Hal MacFie

Consultant in Sensory & Consumer Science

Hal MacFie Training Services
Company Registration No: 7864651
Company Address: 43 Manor Road
Keynsham, Bristol BS31 1RB, UK
Contact Tel: (44) 0117 9863590

About Us!

Structured Experimental Design for Sensory and Consumer Scientists


Course Written by
Anne Hasted
Course Presented by
Anne Hasted & Gemma Hodgson
Qi Statistics Ltd

13th-15th September 2017

56 Commercial Road 
London E1 1LP 

Course Organiser
Hal MacFie
For details and registration e-mail:

This course is aimed at scientists involved in product or process development and optimisation using analytic, sensory or consumer response measures. It will promote this methodology which is generally underutilised in our sector. The standard design methods (DOE) will be discussed together with innovative methods which enable the software to be used for product optimisation based on an unstructured set of products (typical preference mapping data). The aim is as usual to present the techniques and then give attendees the chance to make a small scale trial and analyse and interpret results from real life experiments. Motivation for using the methods will be illustrated with published examples.

The course will be delivered using the software package Design Expert ( but other software solutions will be discussed.

It will also be possible to attend this course from the comfort of your home or office using the Virtual Training Room Facility.


Anne Hasted began her career as an academic statistician at Reading University, leaving in 1989 to set up Qi Statistics Ltd offering statistical support to research and industry. She has over 25 years’ consultancy experience in the food, beverage and personal products industry, particularly in the area of product improvement and is an experienced trainer with a worldwide reputation for “user-friendly” training.

Gemma Hodgson worked in the pharmaceutical industry for over 15 years before joining Qi Statistics in 2012. Gemma now runs Qi Statistics Ltd together with Anne and gives training and consultancy advice to a wide variety of customers from pharmaceuticals, manufacturing, sensory and consumer and general business. Customer feedback has shown Gemma’s approachable attitude are widely valued in a training and consultancy environment.


Day 1 Introduction: Simple Factorial Designs for Identifying key product and process components.

We start with a statistical modelling refresher. Covering modelling with qualitative and quantitative factors. We then introduce multi factor experiments, their objectives and place in a research cycle and their advantages over one at a time experimentation. Simple screening experiments with two levels of each factor Analysis and interpretation of results, the importance of understanding interactions. The last session of the day looks at how smaller fractional experiments can be designed to investigate a larger number of factors using a limited number of samples, explaining the possible pitfalls.

Day 2 Process and Product Characterisation using Response Surface Designs

We now extend to experiments which allow us to characterise the product space with the aim of optimising consumer acceptability or finding product or process recipes that produce particular product characteristics quantified by sensory or analytic data. We investigate the possibility of optimising for several different responses (acceptability/cost/ingredient constraints) and explain the concept of desirability. The particular case where the factors to be considered are proportions of a mixture are also covered.

Day 3 Using DOE methods with unstructured sample sets
Today we look at how the optimisation methods in the software can be applied to a typical preference mapping study where both sensory data (from a trained panel or consumers) and liking data are collected on a set of samples. This allows us to easily visualise the preference space in more than two dimensions and also to identify the optimum product, possibly optimising for several criteria. We also show how design software can be used to objectively select a subset of samples from a sensory profile for consumer testing.

Day 1 Introduction: Simple Factorial Designs for Identifying key product and process components.

Wednesday 13th September


Introductions. Motivation for using experimental design
Efficiency of designs, advantages over “one at a time” approach


Model Refresher
Analysis of Variance for qualitative and quantitative factors, degrees of freedom. Interpretation of ANOVA table, standard errors and LSDs, residual diagnostics. Design-expert practical


Coffee Break


Factorial Experiments-Screening Designs
Designing two level factorial experiments, choosing factor levels, randomisation. Analysis of results: Pareto charts, analysis of variance, model reduction, checking residuals. Interpretation of results




Experiments Using Sensory Panels and Consumer Tests
Incorporation of assessor variation in results to test for effect significance relative to panel/consumer variation


Tea Break


Fractional Designs
Designing experiments with reduced numbers of samples. Classical fractional factorial approach, D-Optimal approach. Discussion on different strategies for consumer testing




Course Dinner


Day 2 Process and Product Characterisation using Response Surface Designs

Thursday 14th September


Response Surface Designs
Classical designs to characterise a response over the product space. Response models, automatic model selection, visualising and interpreting results using individual factor plots, contour plots and 3-D plots. Checking model fit using residuals and panel noise measures. Examples using both liking and sensory data.


Coffee Break


Automatic Response Optimisation using the software – identifying the “sweet spot”. Optimising for several variables simultaneously. The concept of desirability. Industrial case studies




Mixture Designs
Designs where factors are all components of a recipe. Different designs available – which to choose. Analysis and interpretation of fitted models.


Tea Break


You will be given a problem to solve with project objectives and available resources. The aim is to come up with an experimental strategy


Day 3 Using DOE methods with unstructured sample sets

Friday 15th September


Principal Components Refresher
PCA of sensory Data using XLSTAT, rotation of components. Turning product space into experimental factors using PCA


Preference Mapping Using Design Software
Inputting PCA factor data into Design-Ease .Model exploration and evaluation. Using D-Optimal methods to improve the model properties. Visualisation in more than 2 dimensions. Identification of an optimal product in the sensory space


Predicting Sensory Profile of the Optimal product
Using regression modelling (XLSTAT)




Selecting a Sample Subset
Using D-Optimal designs to select a subset of samples from a sensory profile for consumer testing


Course Review


About the Course Venue:

Imparando City of London
Learning Centre
56 Commercial Road
London E1 1LP
United Kingdom


Facility Description:
This is an excellent computer training facility with light and airy rooms, It is 300 metres from Aldgate Underground station on the edge of the City of London close to the Tower of London. There are plenty of hotels close by. Details of the facility can be found at

Please see , entering London E1 1LP into the search box for details of hotels nearby. We usually stay at The Holiday Inn or the Ibis.

Virtual Training Room

Attend training from the comfort of your home or office
Experience all the benefits of instructor-led training without the hassle of traveling. With Virtual Training Room, you can join a live training event from any location—whether you’re in a cube at work or at home, you’ll feel as if you are physically present in the classroom. Advanced classroom technology enables our presenters to deliver the same live instruction to you, whether you’re onsite and offsite.

Why Attend a Flex Class?
Convenience: Where you access a Flex Class is up to you. Join from a satellite classroom, virtual learning cube, home or office. All you need is a standard internet connection and a computer that has a camera and microphone.
Engaging Learning Event: Robust communication tools include two-way, high-definition video and audio, allowing you to interact with your instructor and fellow students as if you were physically present in the classroom.  
Easy-to-Use: No complicated software to buy or learn. The interface is intuitive and easy to navigate. In the event you need assistance, technical support is there to assist you pre, during and post event.
Joining a Virtual Training Room Event is Easy

  • No hardware or equipment to buy or install
  • No special software to learn
  • On call technical support (pre, during and post class)
  • Training prior to event upon request

We will send you a folder with all the class notes and exercises and you will be able to download the data sets. We will be able to watch you doing the exercises.

Yes: Please enrol me in Structured Experimental Design for Sensory & Consumer Scientists 13 - 15 September 2017.

Includes  lunches, course dinner, course materials £2100.00 inc VAT

Virtual Training Room ( This is an additional fee to the course fee which must be paid as well) £500 (inc VAT)

Fees reduced by 5% for members of academia - space limited.


Course Registration Fees



Number of Places

Course Fee Inc VAT


Virtual Training Room Inc VAT


Total: £

    Payments and Refund Policy    

Discounts: We offer a 10 % discount on registrations when two or more people from the same company register for the same course, at the same time.

Registration Policy:  Registration is not final until payment is received. Unpaid spaces will be opened to new registrants 30 days ahead of courses.

Payment:  Payment may be made in, Euros, GB pounds or US Dollars via the Worldpay Gateway or into Currency accounts. Contact for routing and IBAN details of the currency account you require.

Refund policy: Cancellation of registration can be made up to 30 days ahead, and return of payments, minus reasonable administrative expenses, will be made for these cancellations. Cancellations within 15 to 30 days of the course start will receive a credit for a future course. Registrants who fail to attend or cancel less than 15 days prior to the seminar start date are responsible for the entire fee. Substitution of another person for the same course may be made at any time. 

For electronic bank transfers: contact for IBAN details
Mailing address for registration and payment:
Dr H J H MacFie
43 Manor Road
Keynsham, Nr Bristol,
BS31 1RB, United Kingdom

Tel/Fax +44(0)1179863590

Electronic registration forms to

About Us   Contact Us   Legal
worldpay   Free Job Advertising   cards
Copyright © halmacfie 2015