DANISH
CENTER FOR APPLIED
MATHEMATICS
AND MECHANICS
Ph.D.-course
/
Advanced school
The Analysis of Sensory, Consumer and
Questionnaire Data
at
Technical
University of Denmark,
Lyngby,
Denmark
August
14 – August 20, 2011
Organized
by:
DTU
Informatics
Department
of
Mechanical Engineering,
Course Objectives
To improve
the
ability of analysing human perception and questionnaire data. Some of
the
newest statistical methodologies will be covered using the open source
software
R and PanelCheck together with the XLSTAT-PLSPM add-in for Excell
(available in
a 30 days free trial version).
Learning Objectives
|
A student
who has met the objectives of the course will be able to: |
|
·
Work with
R, Panelcheck and XLSTAT-PLSPM ·
Plan and
analyze simple discrimination and similarity experiments using sensR ·
Analyze
replicated discrimination data ·
Perform
and understand simple Thurstonian modeling ·
Use mixed
models for sensory profile data and consumer preference data by
PanelCheck and R-packages. ·
Analyze
sensory profile data with the new scale correction method (using R) ·
Use
PanelCheck for simple analysis as well as multivariate analysis
(including Tucker-1) ·
Analyze
A-not-A and Same-different data ·
Analyze
ordinal discrimination and questionnaire data using the R-package
ordinal ·
Analyze
multivariate questionnaire data by PLSPM methods ·
Design a
network of multivariate relationships ·
Estimate
and assess PLS path models with XLSTAT-PLSPM |
|
|
Language
All lectures will be given in
English.
Organizers
Per Bruun
Brockhoff, B305, R110, (+45) 2044
1711,
pbb@imm.dtu.dk
Line H. Clemmensen, B305, R123,
(+45) 4525 3764, lhc@imm.dtu.dk
This course is offered as part
of the activities of
the DCAMM International Graduate Research School, see www.dcamm.dk.
Program
Day 1, Sunday, August 14:
(All teachers)
14:30 - 15:00 Registration, coffee and rolls.
15:00 - 15:15 Welcome (PBB)
15:15 - 17:00 Student (data) presentations
17:00 - 17:45 R introduction (PBB)
18:00 -
Get-together
Pizza dinner
Day 2, Monday, August 15:
09:15-12:00 Simple
sensory discrimination and
similarity
testing using sensR (PBB)
12:00 - 13:00 Lunch break
13:00 - 17:00 Exercises + project work (PBB, CJ)
Day 3, Tuesday,
August 16:
09:15 - 12:00 Mixed models for sensory and consumer
data using PanelCheck and R (PBB)
12:00 - 13:00 Lunch break
13:00 - 17:00 Exercises + project work (PBB,AK)
Day 4: Wednesday, August 17:
09:15 - 12:00 Panelcheck
Intro, simple and
multivariate
analyses (OT)
12:00 - 13:00
Lunch break
13:00 - 17:00
Exercises + project work (OT)
Day 5: Thursday, August 18:
09:15 - 12:00 Analyzing
Questionnaire data by PLS-
PM
methods (RR)
12:00 - 13:00
Lunch break
13:00 - 17:00
Exercises + project work (RR)
18:00-
Dinner at Tivoli
Day 6: Friday, August 19:
09:15 - 12:00 Advanced
discrimination testing using
R-packages sensR
and ordinal(RHBC)
12:00 - 13:00
Lunch break
13:00 - 17:00
Exercises + project work (RHBC, PBB)
Day 7: Saturday August 20:
09:15 - 12:00 Project
Presentations (All teachers)
12:00 - 13:00 Course
finish Lunch
Course
Main Topics Overview:
Monday:
Simple discimination using R (package
sensR)
Tuesday:
Mixed models using PanelCheck AND R.
(newly developed R-routines)
Wednesday: Multivariate
Analysis using PanelCheck
Thursday:
PLS-PM using XLSTAT-PLSPM
Friday:
Advanced discrimination using R
(packages
sensR and ordinal)
On request,
participants may take part in only some of the days. (Single day
prices:
Academic: 100 EURO, 300 EURO)
Monday, Tuesday
and Friday R is used for the exercises. We do not assume any
R-knowledge in
advance. Participation Friday assumes participation Monday (or at least
similar
knowledge/experience - for people WITH
(sensory) experience in basic discrimination testing, but WITHOUT any
R-experience, there will be some video-recorded tutorials (from the
R-intro
given Sunday, and from Monday, and potentially Tuesday, that with a
little
preparation before Friday morning could bridge the gap).
Teachers:
Professor Per Bruun Brockhoff
(PBB)
PhD Student Rune H.B.
Christensen (RHBC)
PhD Student Christine Jochumsen
(CJ)
PhD Student Alexandra Kuznetsova (AK)
DTU Informatics, Technical
University of Denmark
Research Scientist, PhD Oliver
Tomic (OT)
Nofima Mat, Ås, Norway
Assistant Professor, PhD Rosaria
Romano (RR)
University of Calabria, Italy
Internet resources
For information about teaching
and research at the
DCAMM departments: see http://www.dcamm.dk.
For facts on the Technical
University of Denmark and
visitor's information see: http://www.dtu.dk
For information on the
University of Aalborg see: http://www.aau.dk.
Participants
The course is designed for Ph.D.
students within
Statistics/Data analysis with interest in human perception and/or
questionnaire
data and Ph.D. students within non-statistical areas such as sensory
science,
food science, marketing etc. with interest in data analysis and
statistics.
Study Material
T. Næs, P.B. Brockhoff and O.
Tomic, (2010).
Statistics for Sensory and Consumer Science, John Wiley & Sons.
(SSCS)
Brockhoff, P.B. and Christensen,
R.H.B. (2010).
Thurstonian models for sensory discrimination tests as generalized
linear
models. Food Quality and Preference 21(3), 330-338.
Christensen, R.H.B. Cleaver, G.
and Brockhoff, P.B.
(2011). Statistical and Thurstonian models for the A-not A protocol
with and
without sureness, FQP
22(6), 542-549.
Christensen, R.H.B.
and Brockhoff, P.B. (2009). Estimation and inference in the
same-different test. FQP 20(7), 514-524.
Tomic, O., Nilsen, A. N.,
Martens, M., Næs, T., Visualization
of sensory profiling data for performance monitoring, LWT -
Food
Science and Technology, Vol 40 (2007), pp 262 – 269
T. Dahl, O. Tomic, J.P. Wold, T.
Næs, Some new tools
for visualising multi-way sensory data, FQP 19/1 (2008), 103-113
M. Tenenhaus, V. Esposito Vinzi,
Y.M. Chatelin, C.
Lauro, (2005). PLS Path Modelling, Computational Statistics and Data
Analysis,
48 (1), 159-205
Material, by Day
Sunday:
R intro (http://www2.imm.dtu.dk/~pbb/st113/Module01/R.pdf)
(first part)
Monday:
SSCS, Chap 7
Brockhoff, P.B. and Christensen, R.H.B. (2010). Thurstonian models for sensory
discrimination tests as generalized linear
models. Food Quality and Preference 21(3), 330-338.
Supplementary complete manual and technical
background: (not really necessary to read, but good to know the
existence of)
sensR Reference Manual (http://cran.r-project.org/web/packages/sensR/sensR.pdf)
sensR Technical Reference (http://cran.r-project.org/web/packages/sensR/vignettes/methodology.pdf)
Tuesday:
Relevant SSCS Chapters: 3,5,8,11,12,13
Introduction to mixed models (http://www2.imm.dtu.dk/~pbb/st113/Module01/index.pdf)
Find a video lecture
corresponding to this introduction(http://www2.imm.dtu.dk/~pbb/advancedonlinelectures.html)
Brockhoff, Schlich and Skovgaard (2011). Accounting
for scalinf differences in Sensory Profile Data: Improved Mixed
Model Analysis of Variance (paper draft - to be shared at the
course)
Wednesday:
Relevant SSCS Chapters: 3,4, 5, 14
Tomic, O., Nilsen, A. N., Martens, M., Næs, T., Visualization
of sensory profiling data for performance monitoring, LWT -
Food
Science and Technology, Vol 40 (2007), pp
262 – 269
T. Dahl, O.
Tomic, J.P. Wold, T. Næs, Some new tools
for visualising multi-way sensory data, FQP 19/1 (2008), 103-113
Thursday:
M. Tenenhaus,
V. Esposito Vinzi, Y.M. Chatelin, C.
Lauro, (2005). PLS Path Modelling, Computational Statistics and Data
Analysis,
48 (1), 159-205
Christensen,
R.H.B. Cleaver, G. and Brockhoff, P.B.
(2011). Statistical and Thurstonian models for the A-not A protocol
with and
without sureness, FQP
22(6), 542-549.
Christensen,
R.H.B. and Brockhoff, P.B. (2009). Estimation and inference in the
same-different test. FQP 20(7), 514-524.
Supplementary complete manual and Mixed ordinal models
Tutorial (not really necessary to read, but good to know the existence
of)
ordinal Reference
Manual (http://cran.r-project.org/web/packages/ordinal/ordinal.pdf)
Mixed ordinal
models Tutorial (http://cran.r-project.org/web/packages/ordinal/vignettes/clmm_tutorial.pdf)
Evaluation and Diplomas
To pass the course, active
participation in all
activities is required. Grades:
Pass/Fail. ECTS points: 2.5
Registration
Ask for a
registration form from:
E-mail:
dcamm@mat.dtu.dk.
Registration fee
There is no registration fee for
students enrolled at
universities and public research institutions. For researchers employed
at
universities and public research institutions the registration fee is
250 EURO.
This covers hand-outs, coffee and social events. For all other
participants the
registration fee is 750 EURO.
Deadline
Applicants should submit their
registration to course
secretariat no later than June 30, 2011. You will receive confirmation
within a
week after this date.
Housing
There are a limited
amount of rooms available on the premises of the Technical University
of
Denmark (DTU). These will be offered free of charge to students and
otherwise
at a cost of 25 EURO per night. Accommodation in hostels/hotels can
also be
arranged by the participants themselves.
See the Visit
Copenhagen website at http://www.visitcopenhagen.dk/.
Scholarships:
For Ph.D.-students enrolled at
non-Danish universities and research institutions outside the EU, we
can offer
a limited number of scholarships in order to facilitate participation,
covering
lodging (see above) and extra living costs with a per diem amount of 25
EURO.
Travel expenses will not be covered. Your CV and a short letter of
recommendation from your Ph.D.-supervisor should then be sent in
together with
the application form.
The Danish
Centre for Applied Mathematics and Mechanics, DCAMM is an informal
framework for internationally oriented scientific collaboration between
staff
members at a number of departments at the Technical University of
Denmark (DTU)
and Aalborg University (AAU). The departments cooperating within DCAMM
are:
•
Dept.
of Informatics & Mathematical
Modelling,
DTU
•
Dept.
of Mathematics, DTU
•
Dept.
of Mechanical Engineering, DTU
•
Dept.
of Civil Engineering, AAU
•
Dept.
of Mechanical Engineering, AAU
•
Risø
DTU
DCAMM is an informal
construction. The day to day
activities are coordinated by the Chairman of the Center, while the
formal
governing body of DCAMM is the Scientific Council.
The DCAMM
International Graduate Research School functions within the
standard
framework of the Ph.D. education at the Technical University of Denmark
(DTU)
and at Aalborg University (AAU). Ph.D.-students associated to the
School are
full members of DCAMM through their departments and are enrolled in
relevant
Ph.D.-programs at DTU and AAU.
The School's role is to provide
for an
interdisciplinary framework for education of young researchers in an
international research environment, and the activities are supported by
Danish
Agency for Research, Technology and Innovation (FUU).