ArticlePDF Available

Abstract and Figures

In recent years, many U.S. and Japanese firms have adopted Quality Function Deployment (QFD). QFD is a total-quality-management process in which the “voice of the customer” is deployed throughout the R&D, engineering, and manufacturing stages of product development. For example, in the first “house” of QFD, customer needs are linked to design attributes thus encouraging the joint consideration of marketing issues and engineering issues. This paper focuses on the “Voice-of-the-Customer” component of QFD, that is, the tasks of identifying customer needs, structuring customer needs, and providing priorities for customer needs. In the identification stage, we address the questions of (1) how many customers need be interviewed, (2) how many analysts need to read the transcripts, (3) how many customer needs do we miss, and (4) are focus groups or one-on-one interviews superior? In the structuring stage the customer needs are arrayed into a hierarchy of primary, secondary, and tertiary needs. We compare group consensus (affinity) charts, a technique which accounts for most industry applications, with a technique based on customer-sort data. In the stage which provides priorities we present new data in which product concepts were created by product-development experts such that each concept stressed the fulfillment of one primary customer need. Customer interest in and preference for these concepts are compared to measured and estimated importances. We also address the question of whether frequency of mention can be used as a surrogate for importance. Finally, we examine the stated goal of QFD, customer satisfaction. Our data demonstrate a self-selection bias in satisfaction measures that are used commonly for QFD and for corporate incentive programs. We close with a brief application to illustrate how a product-development team used the voice of the customer to create a successful new product.
Content may be subject to copyright.
Voice of the Customer
Steven P. Gaskin, Abbie Griffin, John R.
Hauser, Gerald M. Katz, and Robert L.
Klein
DEFINITION
The Voice of the Customer (VOC) is a term
used in business to describe the process of
capturing customers’ requirements. The VOC is
a product-development technique that produces
a detailed set of customer wants and needs, which
are organized into a hierarchical structure, and
then prioritized in terms of relative importance
and satisfaction with current alternatives.
The VOC process has important outputs and
benefits for product developers. VOC provides
a detailed understanding of the customer’s
requirements
a common language for the team going
forward
key inputs for the setting of appropriate
design specifications for the new product or
service
a highly useful springboard for product
innovation.
There are four aspects of the VOC
customer
needs, a hierarchical structure, priorities, and
customer perceptions of performance.
DESCRIPTION AND COMMENTARY
VOC studies typically consist of both qualitative
and quantitative market-research steps. They
are generally conducted at the start (or ‘‘fuzzy
front end’’) of any new product, process, or
service design initiative to better understand
the customer’s wants and needs (see
FRONT
END OF INNOVATION
). The VOC can also be a
key input for new-product definition,
QUALITY
FUNCTION DEPLOYMENT (QFD)
,orthe
setting of detailed design specifications (see
PRODUCT SPECIFICATIONS). It is critical that
the product development core team own and be
highly involved in this process. They must be
the ones who take the lead in defining the topic,
designing the sample (i.e., the types of customers
to include), generating the questions for the dis-
cussion guide, either conducting or observing
and analyzing the interviews, and extracting and
processing the needs statements. Only by being
highly involved can the team fully internalize
the VOC and make effective product-design
decisions (see
PRODUCT DESIGN).
As noted in the definition, there are four
aspects of the VOC
customer needs, a hier-
archical structure of the needs, priorities, and
customer perceptions of performance.
1
Customer needs. A customer need is a descrip-
tion, in the customer’s own words, of the benefit
to be fulfilled by the product or service. For
example, when describing diagonal lines on a
computer monitor, a customer might want them
‘‘to look like straight lines with no stair-step
effect.’’ Note that the customer need is not a
solution, such as a particular type of monitor
(XGA, Megapixel, flat screen, flat panel, etc.),
nor a physical measurement (number of notice-
able breaks in the line), but rather a detailed
description of how the customer wants images
to appear on the monitor (Griffin and Hauser,
1993).
2
The distinction between physical measure-
ments and customer needs has proven to be
one of the keys to the success of marketing
tactics. As illustrated in Figure 1, the ‘‘lens’’
model suggests that customers see the world
through the lens of their perceptions (their
needs) (Brunswick, 1952). The lens model says
that customers choose (buy a product or service)
if they prefer that product over others and it is
available to them in the marketplace. However,
preferences are based on how customers perceive
the world. This perception may or may not be
totally accurate. It is based, of course, on the
product’s features, but it is also based on the
image created by advertising, packaging, word
of mouth, social context, and so on. Marketing is
an integrated activity that attempts to design the
product (physical features) and the marketing
to influence customer perceptions. Within the
context of the lens model, the VOC identifies
the dimensions of customer value (customer
needs) and how customers form preferences
with respect to those needs (importance of those
customer needs). The VOC might also identify
how advertising, and so on, affect perceptions,
availability, and perceived price.
Wiley International Encyclopedia of Marketing,
edited by Jagdish N. Sheth and Naresh K. Malhotra.
Copyright © 2010 John Wiley & Sons Ltd
2 Voice of the Customer
Product features
Advertising, and
so on.
Availability,
price
Choice
Perceptions Preferences
Figure 1 The lens model of customer choice.
Knowingcustomerneedsiscriticaltoboth
product development and marketing. For
example, if a product-development team focuses
too early on solutions, they might miss creative
opportunities. A computer-monitor team might
be tempted to focus on the size of the monitor
or the shape. However, readability might
also depend on the ambient room light and
reflections, the colors that the software designer
chooses, the ratio of the height of small letters
to that of capital letters, and even the style of
the typeface (serif or sans serif, proportional or
fixed, etc.). All of these design attributes interact
with the size and shape of a monitor to affect
the customer need of ‘‘easy-to-read text.’’ Some
may be less costly and more effective, some may
be synergistic with changing the monitor’s size
and shape, but all should be considered before a
final design is chosen for the monitor.
Discussions with customers usually identify
75
150 phrases that might be considered an
articulation of customer needs. Such phrases
might include basic needs (what a customer
assumes a monitor will do), articulated needs
(what a customer will tell you that he, she, or
they want a monitor to do), and exciting needs
(those needs which, if they are fulfilled, would
delight and surprise the customer) (see also
KANO
MODEL OF CUSTOMER SATISFACTION
). It is
extremely important that these customer needs
be stated in the customers’ own words, and not in
industry or company jargon, in order to not lose
the meaning.
Identifying customer needs is primarily a
qualitative research task. In a typical study,
between 10 and 30 customers are interviewed
for approximately one hour in a one-on-one
setting. For example, a customer might be asked
to picture him- or herself viewing work on a
computer. As the customer describes his or
her experience, the interviewer keeps probing,
searching for better and more complete descrip-
tions of how he or she views data, images, video,
or anything else, how he or she works with those
images, working conditions, ambient lighting,
and so on. The goal is to experience the experi-
ence of the customer. Sometimes, the interviews
take place at the site where the customer uses the
product
for example, VOC interviews have
been conducted on oil-drilling platforms for
manufacturers of oil-drilling equipment. This
method of data collection is sometimes referred
to as customer visits (McQuarrie, 2008), contextual
inquiry,orethnography.
The interviews are called ‘‘experiential,’’
because they focus on the customers’ experi-
ences. In the interview, the customer might
be asked to voice needs relative to a number
of real experiences. The interview ends when
the interviewer feels that no new needs can be
elicited from that customer.
While it is tempting to simply ask customers,
‘‘What are your needs?’’ customers often have
difficulty articulating them. It is much better
to infer customer needs from experiential inter-
views or observation.
Hierarchical structure. The average marketing
manager cannot work directly with the 75
150
detailed customer needs found in the first step of
the VOC process. A simpler structure is needed
that focuses both strategy and tactics. The
‘‘Voice of the Customer’’ structures customer
needs into a hierarchy of primary, secondary,
and tertiary needs. Primary needs,alsoknownas
strategic needs,arethe2
10 top-level needs that
are used by the team to set the strategic direction
for marketing. Each primary need is elaborated
Voice of the Customer 3
into 310 secondary needs. Secondary needs
indicate more specifically what the marketing
manager must do to satisfy the corresponding
primary (strategic) need. (Secondary needs are
also known as tactical needs.) Tertiary needs,also
known as operational or detailed needs, provide
greater detail so that engineering, R&D, and,
perhaps, the advertising agency, can develop
a detailed set of product characteristics or
advertising copy that satisfies the primary and
secondary needs.
For example, a VOC analysis for movie
theaters identified the following 17 secondary
(tactical needs) structured into 6 primary
(strategic needs):
Theater selection
Offers a good selection of movies and
show times
Easytogetinformationaboutshowtimes
I can always get into the movie I want to
see
A variety of easy and economical ways to
buy tickets
Getting to the theater
The theater is conveniently located
There is safe, convenient parking
Food/refreshments
Good food is available at a fair price
Concessions are well run
The theater building
Quick and easy access to everything I
need
Handles crowds well
Friendly and available customer service
Clean, well-equipped restrooms
A comfortable feeling inside the theater
Inside the theater auditorium
Clean, comfortable seating
Auditoriums are clean
The movie experience
A great view and sound so I’m right in
the action
No disturbances during the show.
There are a number of ways to group the
75
150 tertiary (operational) needs into a more
aggregate set of tactical needs, and then further
into an even smaller set of strategic needs. The
easiest way is to have the product-development
team do so as a group. However, while conve-
nient, this approach has the important limitation
that the results tend to reflect the company’s
organizational chart, that is, how the product
is developed and produced, rather than the
way customers think. It is far better to have
customers group the needs. One way this can
be done is through the use of one or a few
focus groups. A moderator guides the process
and makes sure the groupings make sense and are
sufficiently disaggregate (i.e., that there are suffi-
ciently many tactical needs so that they do not
cover multiple topics). A more statistically repre-
sentative method is to survey a random sample
of current and potential customers and have
them sort the needs individually into piles based
on similarity. This results in a co-occurrence
matrix, which can be analyzed using a hier-
archical clustering routine. The output is a
dendrogram, which shows how the needs should
be grouped for any total number of needs, from
the total number of detailed needs down to two
or more strategic needs. The final number of
primary and secondary needs are then deter-
mined judgmentally on the basis of the output
of the cluster analysis.
Priorities. Some needs have higher priorities
for customers than others. The marketing
manager uses these priorities to make decisions
that balance the cost of fulfilling a customer
need with the desirability (to the customer)
of fulfilling that need. For a movie theater
company, for example, the strategic decision on
whether to provide or communicate improved
movie-viewing experience depends upon the
cost and feasibility of improving the experience
and the priority to the customer of an improved
viewing experience relative to the customer’s
other needs. In the VOC, these priorities
apply to perceived customer needs rather than
product features or engineering solutions. As
an example, a quantitative survey of people
who go to movie theaters yielded the following
importance weights for the 17 secondary needs
(Figure 2).
A number of new techniques have been
developed recently to prioritize customer
needs. One, called teaching agents to choose,
is an incentive compatible direct-elicitation
technique.
3
During the survey, respondents
4 Voice of the Customer
A great view and sound so I'm right in the action
Clean, comfortable seating
No disturbances during the show
Auditoriums are clean
A comfortable feeling inside the theater
I can always get into the movie I want to see
Clean, well-equipped restrooms
Concessions are wellrun
Good food is available at a fair price
Friendly and available customer service
There is safe, convenient parking
Handles crowds well
Quick and easy access to everything I need
The theater is conveniently located
A variety of easy and economical ways to buy tickets
Easy to get information about show times
Offers a good selection of movies and show times
0% 10% 20% 30% 40% 50% 60% 70% 80% 90%
Importance (0100 scale)
100%
Figure 2 Importance ratings for movie theater needs.
give instructions to a hypothetical ‘‘agent’’ about
what rules to use when deciding to choose which
product to buy. Priorities of the needs can be
estimated by tallying the frequency of mention
of the needs referenced in these rules. Another
technique, MaxDiff, involves an exercise where
respondents pick the most and least important of
a series of subsets of needs. The resulting scores
are not subject to scale usage bias, which can lead
to problems, particularly in international studies.
Customer perceptions of performance. Customer
perceptions are also derived from quantitative
market research about how customers perceive
the performance of products that compete in
the market being studied. If no product exists
as yet, the perceptions indicate how customers
now fulfill those needs. (For example, existing
patterns of medical care serve as generic compe-
tition for health-maintenance organizations.
Automobile and bus transportation serve as
generic competition for Southwest Airlines.)
Knowledge of which products fulfill which
needs best, how well those needs are fulfilled,
and whether there are any gaps between the best
product and ‘‘our’’ existing product provide
further input into marketing decisions.
Customer perceptions are often displayed via
a ‘‘snake plot,’’ called so because each product’s
performance ‘‘snakes’’ across the page. These
data are often obtained via a questionnaire in
which each respondent rates each product
(that they consider) on each of the secondary
customer needs.
For example, when people who go to movie
theaters were asked to rate how well the
theater they attend most often performed on
Voice of the Customer 5
0
1
2
3
4
5
6
7
8
9
10
Performance (010 scale)
A great view and sound so I'm right in the action
Clean, comfortable seating
No disturbances during the show
Auditoriums are clean
A comfortable feeling inside the theater
I can always get into the movie I want to see
Clean, well-equipped restrooms
Concessions are wellrun
Good food is available at a fair price
Friendly and available customer service
There is safe, convenient parking
Handles crowds well
Quick and easy access to everything i need
The theater is conveniently located
A variety of easy and economical ways to buy--
Easy to get information about show times
Offers a good selection of movies and show times
Overall
Men
Women
Figure 3 Performance ratings for movie theaters.
the secondary needs, we obtained the plot in
Figure 3.
EXAMPLES OF VOC’S ROLE IN PRODUCT
DEVELOPMENT
During a VOC for the renal division of Baxter
Healthcare, users expressed a need to quickly
understand the nature and seriousness of the
various alarms that typically sounded throughout
the day. The product’s designers developed a
traffic-light device with colored lights that indi-
cated the gravity of the problem at a glance.
A few years ago, Intel, the world’s largest
manufacturer of microprocessors, embarked on
a very public strategy to develop specialized
microprocessors for various applications. To
better understand customer needs surrounding
these applications, the company began to
develop its own VOC. Using a combination of
ethnography and sit-down interviews, followed
by group affinitization processes and large-scale
quantitative prioritization surveys, the company
has now conducted more than 20 such studies on
a host of topics, ranging from extremely simple
consumer applications, to highly advanced
applications with IT Directors at very large
companies.
One of the most compelling products to
emerge from this strategy is the v-Pro micro-
processor for business desktop computers. The
v-Pro technology addresses a number of crit-
ical problems for IT Directors who must manage
a large ‘‘fleet’’ of company computers, and
6 Voice of the Customer
ensure their security from external corruption
and tampering. The v-Pro offers several new
features
which have proven to be extremely
attractive to IT Directors
that emerged from
the identification of key unmet needs in the VOC
process. Launched in mid-2006, the v-Pro
became the fastest product in Intel’s history to
exceed $1 billion in revenue.
PPG Industries, a leading manufacturer
of industrial coatings and other commercial
materials, trained product development teams
across most of its major divisions in the use of
VOC. These teams then conducted a number
of highly successful VOC studies throughout
the world, on topics as diverse as applications
for polyurethane coatings, auto paint used in
body shops, and eco-friendly uses for fiberglass.
Products that emerged from these applications
include a chemical-agent-resistant coating used
in military applications, a new material used
for golf-ball covers, and an advanced fiberglass
product used in wind-power generation. This
latter product allowed PPG to acquire a major
share of this rapidly expanding industry.
As may be seen in these examples, gathering
the VOC is an extremely important part of the
‘‘fuzzy front end’’ of the new-product develop-
ment process. It forms a solid basis for design and
marketing decisions from concept development
through product launch.
ENDNOTES
1
The Voice of the Customer has its origins in
the QFD process, where it is used to develop the
customer needs that are linked to performance
measures. This is why the definition used here
is narrower than the generic use of VOC, which
can refer to customer feedback in any form. See
Griffin and Hauser (1993).
2
Much of the material used here is drawn from
an MIT Sloan Courseware document by John
R. Hauser, ‘‘Note on the Voice of the Customer,’’
MIT, Cambridge, MA 2008. MIT Sloan grants
the nonexclusive right to use this material.
MIT Sloan retains a nonexclusive right to this
material.
3
‘‘Incentive compatible’’ means the incentives
for survey respondents are set up in a way that
they benefit most from responding in a desired
way (in this case, telling the truth).
Bibliography
Brunswick, E. (1952) The Conceptual Framework of
Psychology, University of Chicago Press, Chicago.
Hauser, J.R. and Clausing, D.P. (1988) The house of
quality. Harvard Business Review, 66 (3), 63
73.
Griffin, A. and Hauser, J.R. (1993) The voice of the
customer. Marketing Science, 12 (3), 1
27.
Katz, G. (2001) The ‘‘One Right Way’’ to gather the voice
of the customer. PDMA Visions, 25.
Katz, G. (2004) The voice of the customer, in The PDMA
Toolbook 2 for New Product Development, Chapter 7
(eds P. Belliveau, A. Griffin, and S. Somermeyer),
John Wiley & Sons, Inc., Hoboken.
McQuarrie, E.F. (1998) Customer Visits, Sage Publica-
tions, Thousand Oaks.
McQuarrie, E.F. (2008) Customer Visits,M.E.Sharpe,
New York.
... Chief among its many fables are the irrational claims that feedback -not expertise -is foundational to industrial practice, and that self-reported data is reliable as behavioral insight. The creative injections of statistical analysis to invoke a false sense of scientific validation, the half-misappropriated idea of the 6 ◾ Introduction "voice of the customer" 15 and even the re-branding of survey use as "experience management" -a concept entirely at odds with the available science -are other examples. While survey superstitions remain strong, category participants have begun adding more robust offerings, perhaps recognizing these limitations; nonetheless, the promotional hyperbole remains prevalent. ...
Article
Full-text available
Customer insights play a critical role in innovation. In recent years, articles studying customer insights for innovation have risen in marketing and other fields such as innovation, strategy, and entrepreneurship. However, the literature on customer insights for innovation grew fragmented and plagued by inconsistent definitions and ambiguity. The literature also lacks a precise classification of different domains of customer insights for innovation. This article offers four key contributions. First, it clearly and consistently defines customer insights for innovation . Second, it proposes a “customer insights process” that describes the activities firms and customer insights intermediaries (e.g., market research agencies) use to generate, disseminate, and apply customer insights for innovation. Third, it offers a synthesis of the knowledge on customer insights for innovation along ten domains of customer insights for innovation: (1) crowdsourcing, (2) co-creating, (3) imagining, (4) observing, (5) testing, (6) intruding, (7) interpreting, (8) organizing, (9) deciding, and (10) tracking. Fourth, the authors qualify and quantify the managerial importance and potential for scholarly research in these domains of customer insights for innovation. They conducted 12 in-depth interviews with executives at market research agencies such as Ipsos, Kantar, Nielsen, IQVIA, and GfK to do so. They surveyed 305 managers working in innovation, marketing, strategy, and customer experience. The article concludes with a research agenda for marketing aimed at igniting knowledge development in high-priority domains for customer insights for innovation.
Article
When small business owners in Rwanda start seeking feedback from some of their customers, we find that customers from whom feedback is not sought also respond to changes made by the businesses by increasing their sales at these stores.
Article
Purpose The purpose of this paper is to investigate the role of Customer Participation (CP) in the effectiveness of New Service Development (NSD) by examining the moderating roles of Customer Empowerment (CE) and Customer Satisfaction (CS). The research reduces the risk of failure of the NSD process and/or improves the NSD processes used by companies through the consideration of the results in the practical dimension. Design/methodology/approach This study investigates the effects of CP at different stages of NSD using a quantitative approach. Data were collected through an online survey questionnaire. Smart PLS was used to analyse the data collected from 509 newsreaders and users of the news agency’s application. Findings The model confirmed that CE has an impact on the effectiveness of NSD in the idea generation and commercialization stages, but not in the development stage. Empowerment and customer satisfaction did not influence the three stages of NSD indirectly but directly. The results show that CP, CS and CE do not always have a direct or indirect effect on the development of new services. Therefore, in order to design new service development projects, media news companies need to determine the level of user cooperation. Research limitations/implications The lack of objective data, especially on company performance, forces researchers to use questionnaires to analyse NSD effectiveness. Another limitation is that newspaper users answered the questionnaires, which creates “common method variance.” Practical implications Researchers on NSD effectiveness must use questionnaires due to a lack of objective data, especially on company performance. Another limitation is “common method variance” from newspaper users answering questionnaires. Originality/value This paper is a response to a perceived need for an examination of how new service development can be successful and effective.
Article
Full-text available
Marriott used conjoint analysis to design a new hotel chain. The study provided specific guidelines for selecting target market segments, positioning services, and designing an improved facility in terms of physical layout and services. Based on these strategy and design recommendations, Marriott developed the Courtyard by Marriott concept, which it has successfully test marketed and subsequently introduced nationally. The effectiveness of the study and associated processes also changed Marriott's approach to new product development. Marriott has since developed additional lodging and related products successfully using similar procedures.
Article
Full-text available
The author reviews how methods developed within the information integration paradigm can be used to study consumers' overall evaluations of choice alternatives. Methods are presented for determining the adequacy of several common model forms used to represent overall evaluations: adding, multiplying, and multilinear. Often, more than one integration model can be reconciled with the data by altering one's assumptions about the subjective values of the independent variables and about the relationship between private, unobservable overall evaluations and the overt numerical ratings that index them. Also, different integration models lead to parameter estimates (e.g., part worths) of wrying levels of uniqueness and inter-attribute comparability. Emphasis is given to pinpointing the sorts of evidence and experimental designs that enable one to distinguish empirically among alternative model forms and psychological interpretations of the data-and, conversely, to what interpretations cannot be distinguished empirically-given only overall evaluations of a set of choice alternatives that vary along two or mare attribute dimensions. Finally, the methods described are compared with model diagnosis procedures more commonly used in marketing and consumer research, including compositional correlational techniques and decompositional methods of conjoint measurement.
Article
Full-text available
Disaggregate demand models predict the choice behavior of individual consumers. But while such models predict choice probabilities (0 < p < 1), they must be tested against (0, 1) choice behavior. This paper uses information theory to derive three complementary tests that help analysts select a “best” disaggregate model. “Usefulness” measures the percentage of uncertainty (entropy) explained by the information the model provides. It provides theoretic rigor and intuitive appeal to the commonly used likelihood ratio index and leads to important practical extensions. “Accuracy” is a new two-tailed normal test that determines whether the (0, 1) observations are reasonable under the hypothesis that the model is valid. “Significance” is the standard chi-squared test to determine whether a null model can be rejected. This paper also extends the information test to examine the relationships among successively more powerful null hypotheses. For example, in a logit model one can quantify (1) the contribution due to knowing aggregate market shares, (2) the incremental contribution due to knowing choice set restrictions, and (3) the final incremental contribution due to the explanatory variables. Further extensions provide “explanable uncertainty” measures applicable if choice frequencies are observed. Market research and transportation analysis empirical examples are given.
Article
Robert Cooper and Ulricke de Brentani report the results of their study of firms participating in the industrial financial services industry. Using a self-administered questionnaire, they obtained data on 56 successful and 50 failed products and found that success and failure are strongly associated with eleven important dimensions: synergy, product/market fit, quality of execution of the launch, unique/superior product, quality of execution of marketing activities, market growth and size, service expertise, quality of execution of technical activities, quality of service delivery, quality of execution of pre-development activities, and the presence of tangible elements of the service offering. They report some surprises, including their observation that while new to the firm, products entail more risk than "close to home" ones, the resulting level of success is not sharply reduced.
Article
When populations are cross-classified with respect to two or more classifications or polytomies, questions often arise about the degree of association existing between the several polytomies. Most of the traditional measures or indices of association are based upon the standard chi-square statistic or on an assumption of underlying joint normality. In this paper a number of alternative measures are considered, almost all based upon a probabilistic model for activity to which the cross-classification may typically lead. Only the case in which the population is completely known is considered, so no question of sampling or measurement error appears. We hope, however, to publish before long some approximate distributions for sample estimators of the measures we propose, and approximate tests of hypotheses. Our major theme is that the measures of association used by an empirical investigator should not be blindly chosen because of tradition and convention only, although these factors may properly be given some weight, but should be constructed in a manner having operational meaning within the context of the particular problem.
Article
A pure extinction process memory retrieval latency model is completely characterized by the number of items to be recalled n and the recall rate λ. In this paper λ is allowed to vary across the population of subjects. Results are given for arbitrary individual differences distributions on λ. When λ is distributed gamma the results are very simple and method of moment estimators are easily obtained. In addition the shape parameter of the gamma individual differences distribution turns out to be an index of the degree of heterogeneity of the recall parameter. The pure extinction process model is also appropriate for certain collection and detection tasks.
Article
The general problem of forming composite variables from components is prevalent in many types of research. A major aspect of this problem is the weighting of components. Assuming that composites are a linear function of their components, composites formed by using standard linear regression are compared to those formed by simple unit weighting schemes, i.e., where predictor variables are weighted by 1.0. The degree of similarity between the two composites, expressed as the minimum possible correlation between them, is derived. This minimum correlation is found to be an increasing function of the intercorrelation of the components and a decreasing function of the number of predictors. Moreover, the minimum is fairly high for most applied situations. The predictive ability of the two methods is compared. For predictive purposes, unit weighting is a viable alternative to standard regression methods because unit weights: (1) are not estimated from the data and therefore do not “consume” degrees of freedom; (2) are “estimated” without error (i.e., they have no standard errors); (3) cannot reverse the “true” relative weights of the variables. Predictive ability of the two methods is examined as a function of sample size and number of predictors. It is shown that unit weighting will be superior to regression in certain situations and not greatly inferior in others. Various implications for using unit weighting are discussed and applications to several decision making situations are illustrated.
Article
A model of preferences based on specific product attributes is examined and found to be more powerful than predictions based on personality measures and demographics.