EN ISO 11136:2017

SLOVENSKI STANDARD
01-september-2017
6HQ]RULþQDDQDOL]D0HWRGRORJLMD6SORãQRQDYRGLOR]DL]YDMDQMHKHGRQLþQLK
SUHVNXVRYVSRPRþMRSRWURãQLNRYYQDG]RURYDQHPREPRþMX,62
Sensory analysis - Methodology - General guidance for conducting hedonic tests with
consumers in a controlled area (ISO 11136:2014)
Sensorische Analyse - Methodologie - Allgemeiner Leitfaden für die Durchführung
hedonischer Prüfungen (Verbrauchertests) in einem festgelegten Bereich (ISO
11136:2014)
Analyse sensorielle - Méthodologie - Lignes directrices générales pour la réalisation
d'épreuves hédoniques effectuées avec des consommateurs dans un espace contrôlé
(ISO 11136:2014)
Ta slovenski standard je istoveten z: EN ISO 11136:2017
ICS:
67.240 6HQ]RULþQDDQDOL]D Sensory analysis
2003-01.Slovenski inštitut za standardizacijo. Razmnoževanje celote ali delov tega standarda ni dovoljeno.

EN ISO 11136
EUROPEAN STANDARD
NORME EUROPÉENNE
May 2017
EUROPÄISCHE NORM
ICS 67.240
English Version
Sensory analysis - Methodology - General guidance for
conducting hedonic tests with consumers in a controlled
area (ISO 11136:2014)
Analyse sensorielle - Méthodologie - Lignes directrices Sensorische Analyse - Methodologie - Allgemeiner
générales pour la réalisation d'épreuves hédoniques Leitfaden für die Durchführung hedonischer Prüfungen
effectuées avec des consommateurs dans un espace (Verbrauchertests) in einem festgelegten Bereich (ISO
contrôlé (ISO 11136:2014) 11136:2014)
This European Standard was approved by CEN on 31 January 2017.

CEN members are bound to comply with the CEN/CENELEC Internal Regulations which stipulate the conditions for giving this
European Standard the status of a national standard without any alteration. Up-to-date lists and bibliographical references
concerning such national standards may be obtained on application to the CEN-CENELEC Management Centre or to any CEN
member.
This European Standard exists in three official versions (English, French, German). A version in any other language made by
translation under the responsibility of a CEN member into its own language and notified to the CEN-CENELEC Management
Centre has the same status as the official versions.

CEN members are the national standards bodies of Austria, Belgium, Bulgaria, Croatia, Cyprus, Czech Republic, Denmark, Estonia,
Finland, Former Yugoslav Republic of Macedonia, France, Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania,
Luxembourg, Malta, Netherlands, Norway, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, Sweden, Switzerland,
Turkey and United Kingdom.
EUROPEAN COMMITTEE FOR STANDARDIZATION
COMITÉ EUROPÉEN DE NORMALISATION

EUROPÄISCHES KOMITEE FÜR NORMUNG

CEN-CENELEC Management Centre: Avenue Marnix 17, B-1000 Brussels
© 2017 CEN All rights of exploitation in any form and by any means reserved Ref. No. EN ISO 11136:2017 E
worldwide for CEN national Members.

Contents Page
European foreword . 3

European foreword
The text of ISO 11136:2014 has been prepared by Technical Committee ISO/TC 34 “Food products” of
the International Organization for Standardization (ISO) and has been taken over as
This European Standard shall be given the status of a national standard, either by publication of an
identical text or by endorsement, at the latest by November 2017, and conflicting national standards
shall be withdrawn at the latest by November 2017.
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. CEN [and/or CENELEC] shall not be held responsible for identifying any or all such patent
rights.
According to the CEN-CENELEC Internal Regulations, the national standards organizations of the
following countries are bound to implement this European Standard: Austria, Belgium, Bulgaria,
Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, Former Yugoslav Republic of Macedonia,
France, Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta,
Netherlands, Norway, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, Sweden, Switzerland,
Turkey and the United Kingdom.
Endorsement notice
The text of ISO 11136:2014 has been approved by CEN as EN ISO 11136:2017 without any modification.

INTERNATIONAL ISO
STANDARD 11136
First edition
2014-12-01
Sensory analysis — Methodology
— General guidance for conducting
hedonic tests with consumers in a
controlled area
Analyse sensorielle — Méthodologie — Lignes directrices générales
pour la réalisation d’épreuves hédoniques effectuées avec des
consommateurs dans un espace contrôlé
Reference number
ISO 11136:2014(E)
©
ISO 2014
ISO 11136:2014(E)
© ISO 2014
All rights reserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any form
or by any means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior
written permission. Permission can be requested from either ISO at the address below or ISO’s member body in the country of
the requester.
ISO copyright office
Case postale 56 • CH-1211 Geneva 20
Tel. + 41 22 749 01 11
Fax + 41 22 749 09 47
E-mail copyright@iso.org
Web www.iso.org
Published in Switzerland
ii © ISO 2014 – All rights reserved

ISO 11136:2014(E)
Contents Page
Foreword .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Preliminary considerations . 3
4.1 Study proposal. 3
4.2 Specification of the target population . 4
4.3 Further specifications . 4
5 The consumer sample . 5
5.1 General . 5
5.2 Recruiting the consumers. 5
5.3 Assembling a consumer sample . 7
5.4 Sample segmentation . 7
6 Size of the consumer sample . 8
6.1 Decisions of measurement . 8
6.2 Determining the sample size . 8
6.3 Working with subgroups . 9
6.4 Number of product samples and experimental design . 9
6.5 Safety margin in recruitment . 9
7 Test area .10
8 Products .10
8.1 Anonymous presentation of the products .10
8.2 Preparation and presentation of the products .10
9 Procedures .11
9.1 Two groups of hedonic tests .11
9.2 Rating tests .12
9.3 Paired comparison tests .12
9.4 Ranking test .13
9.5 Additional questions .14
9.6 Instructions for the consumers .14
10 Organization of test sessions .15
10.1 General .15
10.2 Plans .15
10.3 Number of products evaluated in a single session .16
10.4 Nature of the products evaluated within a session .17
10.5 Time of the session .17
10.6 Repetition of a product within a test .17
10.7 Pre-test .17
11 Analysis of the results .18
11.1 General .18
11.2 Inferential analysis .18
11.3 Ratings (see 9.2) .18
11.4 Paired comparisons (9.3) .18
11.5 Ranking (9.4) .18
ISO 11136:2014(E)
12 Study report .19
12.1 General .19
12.2 Products .19
12.3 Test procedure .20
12.4 Consumers .20
12.5 Results .21
12.6 Annexes to the report .21
Annex A (informative) Example of a recruitment questionnaire .22
Annex B (informative) Methods for evaluating the data of segmentation subgroups .26
Annex C (informative) Plans for assigning products to consumers .28
Annex D (informative) Influence of the sample size on the accuracy of one mean .29
Annex E (informative) Minimum sample size for tests using rating.30
Annex F (informative) Minimum sample size for tests using ranking .34
Annex G (informative) Examples of data analysis for ratings .36
Annex H (informative) Examples of data analysis for rankings .41
Bibliography .43
iv © ISO 2014 – All rights reserved

ISO 11136:2014(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of any
patent rights identified during the development of the document will be in the Introduction and/or on
the ISO list of patent declarations received (see www.iso.org/patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation on the meaning of ISO specific terms and expressions related to conformity
assessment, as well as information about ISO’s adherence to the WTO principles in the Technical Barriers
to Trade (TBT) see the following URL: Foreword - Supplementary information
The committee responsible for this document is ISO/TC 34, Food products, Subcommittee SC 12,
Sensory analysis.
INTERNATIONAL STANDARD ISO 11136:2014(E)
Sensory analysis — Methodology — General guidance for
conducting hedonic tests with consumers in a controlled area
1 Scope
This International Standard describes approaches for measuring, within a controlled area, the degree to
which consumers like or relatively like products.
It uses tests based on collecting consumers’ responses to questions, generally on paper or via a keyboard
or a touch screen. Tests of a behavioural nature (such as recording quantities consumed ad libitum by
the consumers) do not fall within the scope of this International Standard.
The hedonic tests dealt with in this International Standard, can be used as a contribution to the following:
— comparing a product with competitor products;
— optimizing a product so that it obtains a high hedonic rating or is liked by a large number of consumers;
— helping to define a range of products to correspond to a particular consumer target population;
— helping to define a best-before date;
— assessing the impact of a product formulation change on the pleasure given by the product;
— studying the impact of sensory characteristics of a product on degree to which it is liked,
independently of the product’s extrinsic characteristics, such as brand, price, or advertising;
— studying the effect of a commercial or presentation variable, such as packaging.
The methods are effective for determining
— whether or not, a perceptible preference exists (difference in degree of liking), or
— whether or not, no perceptible preference (paired similarity test) exists.
2 Normative references
The following documents, in whole or in part, are normatively referenced in this document and are
indispensable for its application. For dated references, only the edition cited applies. For undated
references, the latest edition of the referenced document (including any amendments) applies.
ISO 4121, Sensory analysis — Guidelines for the use of quantitative response scales
ISO 5492, Sensory analysis — Vocabulary
ISO 5495, Sensory analysis — Methodology — Paired comparison test
ISO 8587, Sensory analysis — Methodology — Ranking
ISO 8589, Sensory analysis — General guidance for the design of test rooms
ISO 29842, Sensory analysis — Methodology — Balanced incomplete block designs
3 Terms and definitions
For the purposes of this document, the terms and definitions given in ISO 5492 and the following apply.
ISO 11136:2014(E)
3.1
access panel
sample database of potential respondents who declare that they will cooperate for future data
collection if selected
[SOURCE: ISO 20252]
Note 1 to entry: Respondents can be drawn on a more or less regular basis.
3.2
closed-ended question
question requiring respondents to select from a predetermined list of possible answers
3.3
commissioning party
person, body, or service who commissions a third party to conduct a study
Note 1 to entry: The concept of commissioning party corresponds to that of purchaser or customer in quality
control. It contrasts with that of the supplier, service provider, or laboratory
Note 2 to entry: Usually, the commissioning party and the service provider belong to different enterprises. Where
they belong to two departments of the same enterprise, the respective responsibilities of the two departments
shall be carefully differentiated and explicitly clarified in the study proposal
3.4
consumer
respondent
person who uses a product
Note 1 to entry: For the purposes of this International Standard, the meaning is restricted to a person who is
neither an expert, an expert sensory assessor nor a selected assessor in conformity with ISO 5492.
3.5
consumer sample
group of consumers recruited on the basis of criteria specified by the nature of the target population
3.6
controlled area
location providing
— controlled preparation and presentation of the products,
— comfortable conditions for consuming the products and for questioning the consumers, and
— absence of communication (verbal and non-verbal) between the consumers, guaranteeing
independent responses
3.7
hedonic perception
amount of pleasure given by the sensory properties of a product
3.8
hedonic test
test aimed at measuring the overall hedonic perception of a product by consumers
3.9
open-ended question
question that does not provide ready-made alternatives for respondents but asks them to answer in
their own words
Note 1 to entry: It can concern each of the products presented to the consumers or only some of them (e.g. when
the question asks why a particular product has appealed most, or least, to an consumer).
2 © ISO 2014 – All rights reserved

ISO 11136:2014(E)
3.10
position bias
bias related to the location of a product in a set of products being evaluated
3.11
product family
group of products that can replace one another under normal conditions of consumption
Note 1 to entry: Product families may vary according to culture and consumption habits.
3.12
representativeness
degree to which attributes of the sample agree with relevant attributes of the population
from which it is drawn
3.13
sequential bias
bias related to the temporal or sequential position of a product in a set of products being evaluated
3.14
session
meeting of consumers working simultaneously according to the same protocol during a defined time period
Note 1 to entry: A session can be divided into several subsessions separated by a defined rest time. For example, a
session lasting 1 h 30 min can be divided into two subsessions with a 10-min break between them.
3.15
target population
population whose hedonic response to a product is to be evaluated
4 Preliminary considerations
4.1 Study proposal
The study proposal is drawn up by the service-providing laboratory based on the information (especially
concerning the objective of the study and target population) given by the commissioning party, as a
written document that binds the laboratory and the commissioning party contractually. It includes the
following elements:
— the objective of the study;
— the products to be evaluated (and the procedures for their procurement, especially when the
laboratory has to procure one or more products);
— the target population for the study;
— the size of the consumer sample (sample size) and the way it is to be recruited;
— any limitations on consumers’ prior history of participation in consumer studies;
— any limitations on other products to be evaluated in the same testing session;
— the evaluation conditions;
— the type of interview (self-completion forms or interviewers);
— the questionnaire;
— the place of evaluation;
ISO 11136:2014(E)
— the number of products to be evaluated per session in the proposed study, together with an
indication of other products to be evaluated where the session comprises several product families
(where these products are not known at the time of drawing up the proposal, the laboratory should
be committed to communicate them as soon as the laboratory knows the nature of the products);
— the conditions of preparation specific to the products to be evaluated (if they are known at this stage);
— any instructions specific to the products to be evaluated (if they are known at this stage) together
with any specific information to be given about the products or the test at the start of the session;
— the name of the statistical tests to be used for interpreting the results; the type of risks used and
their tolerable values; the magnitude of the minimum difference to be detected in a difference of
liking test or of the maximum tolerable difference in a similarity of liking test;
— any envisaged segmentation of the consumer population, based either on characteristics known
before obtaining judgment data or from the responses obtained;
— the method of examining and summarizing open-ended questions;
— any recommendations the commissioning party wishes the laboratory to draft on the basis of the results;
— the dates envisaged for the tests and for submission of the report.
When any of the above elements are unknown at the time of the study proposal, the proposal includes for
each element concerned the following statement: “This element will be specified by the commissioning
party by. [specifying the stage of the study].”
NOTE If a specification already exists, the study proposal may make reference to it without repeating
technical points described in an operational manner in the specification.
4.2 Specification of the target population
In order to specify the target population, it is necessary to answer the following questions. These
questions shall be considered for each test to be performed because the consumer target group can be
different from one test to the next, even for the same product.
— Has the product to be tested already been introduced on the market? If so, is it possible to distinguish
between actual and potential consumers?
— Are the consumers of interest those who actually use the product, potential consumers who have
not been using the product or both groups?
— Are results from specified subgroups to be examined and compared?
— Are the results of the total consumer sample to be analysed with a view identifying subgroups?
— Are differences between the results of individuals of interest?
4.3 Further specifications
Subsequent to specifying the target population, the following aspects shall be specified:
— place of test (see Clause 7);
— expected precision of measurement (see 6.1);
— test method (see Clause 9);
— product presentation plan for the test methods selected (see 10.2);
— specifications for the hypothesis to be tested (see 6.1);
4 © ISO 2014 – All rights reserved

ISO 11136:2014(E)
For the hypothesis to be tested, the following aspects shall then be specified:
— the composition of the consumer sample(see Clause 5);
— the size of the consumer sample (see Clause 6).
5 The consumer sample
5.1 General
A hedonic test aims to determine the acceptability of the products and/or to determine preferences
among two or more products by the specified consumer population.
The composition of the consumer sample is decisive for any hedonic test as regards whether or not the
result can answer the questions of interest to the commissioning party.
The consumers shall be volunteers, which does not imply that it is not permitted for them to receive
expenses or a reward for participation.
It is essential to obtain spontaneous reactions.
Trained consumers shall be excluded from these tests since they are likely to differ systematically from
the target population.
It is usually inadvisable to recruit a consumer sample from the personnel of a company manufacturing
the products to be tested. The factors most likely to distort the results when an in-house consumer
panel is used are
— a risk of the products to be tested being recognized,
— a tendency to judge in favour of the recognized products, and
— excessive familiarity with the products.
These factors carry a serious risk of the results not being representative for the target population
of consumers.
Any criteria to be followed when selecting the consumers (e.g. whether or not they may be recruited
from the staff of the manufacturing company or its competitors or from a particular socio-economic
sector) shall be agreed with the client ordering the test irrespective of the recruiting method used.
5.2 Recruiting the consumers
5.2.1 General
WARNING The following shall be observed.
— Confidentiality shall be observed and relevant legislation shall be complied with when
creating and documenting files containing personal data.
— Legislation with respect to age restrictions shall be adhered to.
Consumers can be recruited either on a task-specific basis (where consumers are freshly recruited for a
particular study) or from an access panel (a list of potential consumers having known characteristics).
Task-specific recruitment has often been considered a means of recruiting consumers who have
not participated much in consumer studies, but this idea might have become erroneous with the
multiplication of locations where hedonic tests are organized in a quasi-permanent manner.
ISO 11136:2014(E)
5.2.2 Task-specific recruitment
Task-specific recruitment can be conducted in a public place, at a sales point, by telephone, by mail
or electronic mail or by advertisement in a local newspaper or radio station, or by social network or
other internet ways. In many cases, it is necessary to reach a prior agreement with the corporation or
organization responsible for the area in which the recruitment occurs.
The manner of recruiting and the time of approaching the consumers (in particular when making contact
at public places or by phone and when distributing information through the media) can have a strong
effect on the composition of the consumer sample.
5.2.3 Recruitment from an access panel
For efficiency in recruiting, it is also possible to assemble an access panel in the form of a file of consumer
descriptions. Prior to each test and subsequent to specifying the target group, a pre-selection can be
made based on criteria recorded in the file.
A consumer description may include consumer data such as the following:
— identity details of the person concerned, contact data;
— age, gender;
— marital status, household composition;
— social situation, profession, income;
— possible health problems (e.g. on allergies, diabetes, vision impairments, etc.) relevant to the
products to be tested;
— other information relevant to the products to be tested (e.g. eating or drinking habits, religious
prohibitions, lifestyle, household equipment);
— information on the person’s availability for participation in tests;
— information on previous participation(s) in consumer tests.
Every consumer description shall be updated at regular intervals.
Such a database allows an efficient dialogue between the commissioning party and the service provider
insofar as it enables the latter to ensure, a priori, that the initial desires of the commissioning party
regarding target consumers can be satisfied.
5.2.4 Frequency of employing the consumers
In comparison to task-specific recruitment, there is a greater risk of “consumer professionalizing” when
recruiting from an existing pool of consumers.
It is important to avoid a training effect for the individual consumer in relation to the product group
concerned. Therefore, the same consumers shall not be employed too often. As guidance, an interval of
at least three months between individual tests on the same product is recommended.
The laboratory shall keep records of each consumer’s frequency of participation in tests involving each
product and each product family. The participation history of the consumers shall be included in the
study report, possibly including information about the product families involved if requested by the
commissioning party.
6 © ISO 2014 – All rights reserved

ISO 11136:2014(E)
5.3 Assembling a consumer sample
5.3.1 Selection of consumers by means of recruitment questionnaires
When consumers are selected by means of a recruitment questionnaire relating to criteria stipulated
for the composition of the consumer sample, it shall not be possible for the consumer to identify which
criteria in the questionnaire are decisive for selection to participate in the test.
The following are examples of possible criteria:
— previous participation in testing the product group concerned;
— frequency of using the product ;
— the product brand usually used, product description, place of purchase, etc.;
— habits in the use or consumption of the product.
Other criteria, such as age, sex, social stratum, occupational group, or geographical location can be
relevant. For reasons of practicability, classes should be specified for each of these criteria. For each
class, a percentage should be stated by which this class is to be represented in the consumer sample.
For each consumer selected to take part in the test, the recruitment questionnaire shall be filled out
completely.
The required recruitment details may be verified.
An example of a recruitment questionnaire is given in Annex A.
The recruitment questionnaire shall be preserved, or information arising therefrom shall be stored to
ensure the traceability of recruitment parameters of the study.
5.3.2 Representativeness of the consumer sample
Representativeness with respect to the target population is the foremost quality required of a sample.
Defining this population generally results from a concerted action between the study-commissioning
party who proposes a target population and the laboratory which evaluates the feasibility of
implementing this proposal.
To select consumers who are representative of the target population, criteria such as the following
shall be used:
— frequency of use or consumption of the product (this criterion is often considered fundamental on
account of its supposed influence on the discriminating power of the study);
— age, gender, socio-economic status, occupation, geographical location;
— brand of product usually used or consumed;
— place of purchase of the product.
5.4 Sample segmentation
There are two ways in which the consumer sample can be segmented:
a) Segmentation at the outset in order to obtain answers to questions such as the following:
1) Do women respond in the same way as men?
2) Are responses different for different age groups?
3) Do responses depend on consumption habits?
ISO 11136:2014(E)
In this case, each subgroup is analysed separately and the results are compared.
b) Segmentation may be derived from the data collected if there is evidence (such as multimodality) of
different subgroups.
In Annex B, guidance is given as to how to deal with segmentation data.
6 Size of the consumer sample
6.1 Decisions of measurement
The numerical precision of any averages or estimates obtained from the results increases with sample
size. However, increased precision of measurement does not in itself ensure the relevance and validity
of conclusions reached. Appropriate choices of consumers and procedures are also essential.
Annex D contains some considerations on the influence of the consumer sample size on the precision
of measurement.
Precision also depends on the variability of the consumers in their responses to a single product. The
larger the dispersion, the larger the sample size shall be to achieve a given precision. Knowledge of this
parameter comes from the experience of both the laboratory and the commissioning party.
The precision of the results depends also on the test procedure. For example, all other things being
equal, the difference between two products is established more precisely if each consumer assesses
both products rather than if they are judged by different consumers.
The required precision depends on the purpose of the test. With all other things being equal, it is
influenced by the following:
— the smallest difference between two mean pleasure ratings that is considered large enough to be useful
when the purpose is to demonstrate a difference (the smaller it is, the larger the sample size has to be);
— the greatest difference between two mean pleasure ratings that is considered small enough to be
ignored, when the purpose is to demonstrate equivalence (the smaller it is, the larger the sample
size has to be);
— the risk, α, that the commissioning party is willing to accept of mistakenly concluding that there is
a difference (the smaller the risk, α, the larger the sample size has to be);
— the power, P, that the commissioning party desires for the test. (P = 1 – β, where β is the risk of
mistakenly concluding that there is no difference); the larger the desired power, the larger the
sample size has to be);
— the directionality of the intended statistical test. If the commissioning party is interested only in
reassurance that product B is not inferior to product A, a directional test is appropriate and the
power of the test is greater than if the conclusions that B is inferior to A or that B is superior to A
would be of equal interest.
6.2 Determining the sample size
Determining the sample size is a critical step in the development of a test and demands the assistance
of a statistician. Annex E gives expressions (accompanied by examples) which can be used for the
calculations for either a difference test or a similarity test based on ratings. Annex F does the same for
tests based on preferences.
In all cases, the size of a consumer sample conforming to this International Standard shall never be
less than 60.
Where the laboratory does not have the information required by the methods described in Annex E or
Annex F, this International Standard fixes the minimum sample size at 100.
8 © ISO 2014 – All rights reserved

ISO 11136:2014(E)
Where the laboratory uses the methods described in Annex E or Annex F, the sample size is given by the
calculation result. However, this number
— can be lowered to 100 when the calculated number of consumers is over 100, but the laboratory
and/or the commissioning party does not have the means to question a larger number of consumers.
If this occurs, the laboratory shall calculate the estimated power of the test for a number of
consumers equal to 100 and obtain the agreement of the commissioning party that this lower power
is acceptable, and
— shall be increased to 60 when the calculated number of consumers is below 60.
The values of 100 and 60 suppose that the commissioning party does not hope for conclusions segmented
according to consumer characteristics such as age or gender. Where a segmentation is decided on prior
to the test, the minimum number of consumers per segment is 60.
6.3 Working with subgroups
6.3.1 General
Subgroups of the consumer sample can be formed before collecting test data or by making use of test
data. For any of the options listed below, statistical advice should be obtained at the design stage.
6.3.2 Separate tests using pre-formed consumer groups
The commissioning party may wish to study separate subgroups formed by taking account of consumer
characteristics (such as gender or age), which are known before conducting the test. One option is to
analyse their results independently. If this is done, each subgroup shall consist of at least 60 consumers.
6.3.3 Unified test using pre-formed consumer groups
The procedure in 6.3.2 is less efficient than balancing presentations over the whole consumer sample,
followed by an integrated analysis of all the results that takes account of subgroup membership. The
same degree of confidence will normally be achieved with fewer than 60 consumers in each subgroup.
This style of analysis is at its most efficient when all subgroups are of the same, or of very similar, size.
6.3.4 Segmentation of the consumers
The membership of subgroups may be an outcome derived from the results of a test on a large consumer
sample. The subgroups are then classes resulting from the evaluation of all the data on hand (measurement
results and/or socio-demographic data). This segmentation serves to describe the consumer sample and
can be used for developing new hypotheses. The number of groups formed, their characteristics, and
their sizes all depend on the amount and nature of the results obtained.
6.4 Number of product samples and experimental design
The number of samples and the experimental design affect the size of the consumer sample. If a complete
plan is used for product presentation, the number of consumers needed for the test is equal to the
number of responses per product to be obtained. If an incomplete plan is used, the number of consumers
must be larger.
6.5 Safety margin in recruitment
The number of responses actually obtained is usually smaller than the numbe
...