Niharika Agarwal(F- 116 )

Saurav Barua(F - 131 )

Mohit Khanna(F-42)
Aman Kumar Singh(F - 152)

CONJOINT ANALYSIS: TO
FIND AN OPTIMUM
COMBINATION OF
FEATURES FOR
SMARTPHONES

Contents
Introduction:............................................................................................................... 3
Types of Conjoint Analysis.......................................................................................... 4
Usages of Conjoint Analysis........................................................................................ 4
Industry Analysis........................................................................................................ 4
Problem Statement..................................................................................................... 7
Methodology:.............................................................................................................. 7
Literature Review....................................................................................................... 8
Questionnaire:.......................................................................................................... 10
Overall Statistics...................................................................................................... 12
Conclusion & Limitations.......................................................................................... 18
References:............................................................................................................... 19

Introduction:
Conjoint analysis is a statistical technique used in market research to
determine how people value different features that make up an individual
product or service.
The objective of conjoint analysis is to determine what combination of a
limited number of attributes is most influential on respondent choice or
decision making. A controlled set of potential products or services is shown
to respondents and by analyzing how they make preferences between these
products, the implicit valuation of the individual elements making up the
product or service can be determined. These implicit valuations (utilities or
part-worths) can be used to create market models that estimate market
share, revenue and even profitability of new designs.

Conjoint originated in mathematical psychology and was developed by

marketing professor Paul Green at the University of Pennsylvania and Data
Chan. Other prominent conjoint analysis pioneers include professor V.
Seenu Srinivasan of Stanford University who developed a linear
programming (LINMAP) procedure for rank ordered data as well as a selfexplicated approach, Richard Johnson (founder of Sawtooth Software) who
developed the Adaptive Conjoint Analysis technique in the 1980s and Jordan
Louviere (University of Iowa) who invented and developed Choice-based
approaches to conjoint analysis and related techniques such as MaxDiff.
Today it is used in many of the social sciences and applied sciences
including marketing, product management, and operations research. It is
used frequently in testing customer acceptance ofnew product designs, in
assessing the appeal of advertisements and in service design. It has been
used in product positioning, but there are some who raise problems with this
application of conjoint analysis (see disadvantages).
Conjoint analysis techniques may also be referred to as multiattribute
compositional modelling, discrete choice modelling, or stated preference
research, and is part of a broader set of trade-off analysis tools used for
systematic analysis of decisions. These tools include Brand-Price TradeOff, Simalto, and mathematical approaches such as AHP, evolutionary
algorithms or Rule Developing Experimentation.

How Conjoint Analysis works ?

Decompose the overall utility into its individual attributes part- worths
Additive model- Overall utility = Sum total of all part- worths
Total worth/ Utility = Part- worth of level i for factor 1+
Part- worth of level j for factor 2 + . Part- worth of level n
for factor m
Interaction model- Overall utility > Sum total of all part-worths
Total worth/ Utility = Part- worth of level i for factor 1+
Part- worth of level j for factor 2 + . Part- worth of level n
for factor m + I (Interaction effect between the attributes
and their level)
Generally, the Traditional Conjoint analyses use additive models
whereas ACA and CBC use interaction models

Types of Conjoint Analysis

Full Profile Method- Analysis carries on based on the respondents
evaluation of all the possible combinations in the stimuli.
Fractional Factorial Design- Method of designing a stimuli that is a
subset of the full factorial design so as to estimate the results based on
the assumed compositional rule.
Pair wise Comparison Method- Method of presenting a pair of
stimuli to the respondent for evaluation, with the respondent selecting
one of the stimuli as preferred.
Self-Explicated Model- Compositional technique where the
respondent provides the Part- Worth estimates directly without making
choices
Adaptive (Hybrid) Conjoint Analysis (ACA)- ACA asks respondents
to evaluate attribute levels directly, and then to assess the importance
of each attribute, and finally to make paired comparisons between
profile descriptions.
Choice Based Conjoint (CBC)- An alternative form of conjoint
analysis where the respondents task is of choosing a preferred profile
similar to what he would actually buy in the marketplace. CBC analysis
lets the researcher include a "None" option for respondents, which
might read "I wouldn't choose any of these."
Fractional Factorial Design- Method of designing a stimuli that is a
subset of the full factorial design so as to estimate the results based on
the assumed compositional rule.

Usages of Conjoint Analysis

Breaking down customers overall utility from the product into values
put in by him on the products individual attributes.
Product planning and design
Accommodating conflicting interests Buyers want all of the most desirable features at lowest possible
price
Sellers want to maximize profits by:
Minimizing the costs of features provided
Providing products that offer greater overall value than the
competitors.

Market segmentation based on the utility structures

Industry Analysis
India is the second largest mobile handset market in the world after China
and is poised to become an even larger market with unit shipment of INR
208.4 million in 2016 at a compound annual growth rate (CAGR) of 11.8 per
cent from 2010 to 2016. The mature Indian mobile consumers increasing
preference for high-end handsets and the younger demographics desire to
use mobile Web 2.0 technologies could see the market revenues soar from
INR 255.91 billion in 2010 to INR 350.05 billion in 2016. With end users need
for converged devices and original equipment manufacturers (OEMs)
accelerated adoption of open-source operating systems (OSs) such as
Android and Symbian, the mobile handset-smartphone combination is
emerging as the future growth engine of the telecom industry. The Indian
Phone market has grown by 24 % YoY in 2013 Q1 whereas the smartphone
market grew 74 % in 1st quarter 2013 Y-o-Y.
In 2011, the mobile market is likely to witness almost a three-fold increase in
the number of participants. This is expected to result in a price war and a
consequent squeezing of profit margins. In 2010, the decline in the average
selling price (ASP) of mobiles by 11.3 per cent opened up possibilities of
market consolidation. The intense competition is also compelling handset
manufacturers to enhance the application ecosystem and invent products.
While market entrants are likely to be daunted by the sheer numbers in the
market, they will identify abundant opportunities in the rural and semi-rural
market for the next three to four years. For the mobile handset market, the
rural market offers exciting prospects due to its significant uptake of feature
phones, says the analyst of this research. The rural and semi-rural markets
accounted for 65 per cent of sales for most Indian manufacturers in FY2010.
In the case of smartphones, most existing global brands are concentrating on
building application stores and improving service quality to offer an
attractive value proposition and strengthen their market position. Entrants
will be particularly focused on branding, as a smartphone is a highinvolvement product and the brand is a vital purchase criterion. While
smartphone consumers are also price conscious, it will not be possible for
manufacturers to subsidise due to the operation of an open market rather
than an operator-leveraged distribution model. Moreover, 70 per cent of the
Indian population consumes only voice services, and mobile data services
have not yet achieved large-scale popularity. However, this is set to change
with the reduction of mobile Internet charges by telecom service providers
and the introduction of 3G in India. The market is also witnessing the influx
of a new class of affordable handsets, which are classified as smartphonelike devices, with touch screens and other smartphone features.

In the next five years, the revenue share of smartphones in the mobile
handset market is expected to rise steadily, as an increasing number of
participants are targeting this space for higher margins, notes the analyst.
This trend is likely to persist, as numerous handset manufacturers are
strategizing to deploy more smartphone models in their portfolio. In the
smartphone market, applications will be a key differentiating factor. The midtier price bracket is likely to experience high uptake and hence,
manufacturers should strategize on deploying more models in this category.
Market Sectors
Expert Frost & Sullivan analysts thoroughly examine the following market
sectors in this research:
Mobile

Ultra Low-cost Mobile Handsets (ULCMHs)

Low-to Medium-cost Mobile Handsets (LCMHs)

High-cost Mobile Handsets (HCMH)

India Smartphone Shipments by Operating System - 2012 Q1 and

2013

Top-Five India Smartphone Vendors Share,2013 Q1

Problem Statement
The objective is to find an optimum combination of features most sought
after by people looking to buy a smartphone so that companies can work on
providing these features at an affordable price and improving customer
satisfaction while reducing costs incurred from other redundant features.

Methodology:
The following is the methodology that was adopted by us for finding out the
utilities of various attributes:

Stage 1
Identify the research
problem

Stage 2
Decide on the
attributes and their
levels
Focused Group is the
most practiced

Stage 3
Chose the
methodology
Traditional Conjoint
analysis

Stage 6
Interpret results

Stage 5
Run analysis
Individual or
aggregative

Stage 4
Collect responses
Rating or rank order

Stage 7
Validate the results
External or internal
validity tests

Stage 8
Apply the Conjoint
results
Product designing,
market segmentation
etc.

We have used Fractional Factorial Design. It is a Method of designing a

stimuli that is a subset of the full factorial design so as to estimate the
results based on the assumed compositional rule.

Literature Review
Conjoint Analysis and MDS approach to brand improvement of an aerosol
product
Authors: Vincent Charles, Mukesh Kumar & Tulika Anand, Journal of centrum
Cathedra

The purpose of this study is to identify feasible offerings of aerosols from a

companys point of view and the positioning of a comparatively new brand of
room air freshener among all other existing brands in the capital city of Bihar
(Patna) in India. The study makes use of conjoint analysis and the
multidimensional scaling technique to identify:
1. The attributes of the room air freshener and their corresponding levels
from the consumers perspective
2. The importance of each attribute of the room air freshener and its
contribution in influencing the consumers purchase decision
3. the best and the worst combinations of attributes and their levels from
the consumers point of view, and
4. the potential opportunities for the new brand of room air freshener in
the perceptual map of the consumers mind
The authors have tried to understand the requirements and needs on
management as well as from customers point of view. From managements
perspective they aim:
To understand the feasible offerings of the aerosol product (room air
freshener);
To identify the position of the ZZZ room air freshener in the minds of
consumers and to identify the potential opportunities for the brand
ZZZ.
From customers perspective they aim:
to identify the attributes of the aerosol product and their levels;
to identify the importance of each attribute and its corresponding
levels;
to identify the consumers preferences from all possible combinations
of attributes of the aerosol product;
to identify the brand positioning of current brands of room air
fresheners available in the Patna region on the selected dimensions;
to look for gaps in the spatial map in order to identify potential
opportunities for the brand ZZZ room air freshener.
Findings:
In this study, the room air freshener attributes identified as important in
influencing the consumers purchase decision are fragrance, longevity of the
fragrance stay, spray point inclination, price, pack design, and bottle
material. Of these attributes, fragrance was found to be the most important
attribute in influencing the purchase decision, followed by longevity, price,
pack design, spray point inclination, and bottle material. The best
combination of the attributes, according to the consumers, is the
combination of Sandalwood fragrance, fair price, longevity of at least 6
hours, and pack design with cap, forward spray point inclination, and glass
bottle material. The study also revealed that fragrance, price, and longevity
of the fragrance stay significantly influence the consumers purchase

10

decision while the other attributes do not significantly influence such

purchase decision.
The use of Conjoint Analysis to determine consumer buying preferences
Authors: Ernest North and Retha de Vos
The main aim of this article was to provide overview of nature and use of CA
as a research tool, and to indicate its value when, for example a researcher
wishes to analyse female consumers apparel purchasing decision based on
the value they attach to certain attributes when making a purchasing
decision. Although the apparel industry has reached maturity and growth is
very slow, fashion trend cycles are accelerating. The presence of more and
more brands has created a competitive environment unheard of in the past.
Findings:
Multiple discriminant analysis helps to understand and explain research
problems that involve a single categorical dependent variable and several
metric independent variables. A mixed data set is also possible for the
independent variables if the non-metric variables are coded (Hair et al,
1998:321). According to Hair et al (1998:436) conjoint analysis places more
emphasis on the ability of the researcher or manager to theorise about the
behaviour of choice than it does on analytical techniques. Thus it should be
viewed primarily as exploratory, because many of its results are directly
attributable to basic assumptions made during the course of the design and
the execution of the study. The critical interplay between the assumed
conceptual model of decision-making and the appropriate elements of the
conjoint analysis makes this a unique multivariate method (Hair et al,
1998:436).
Consumer Preferences for Quality Attributes of Rice
Author: B.R. Walisinghe and L.H.P. Gunaratne
In this research consumer preferences for different quality attributes of rice
were assessed based on conjoint methodology. The appropriate attributes
and levels were identified from a focus group discussion and subsequently a
conjoint questionnaire was administered using a sample of 185 consumers
under a fractional factorial design. ANOVA and part worth utility models were
estimated. The relative importance of attributes was calculated using partworths. ANOVA results indicate that of the four attributes, type, color and
purity were significant, but price was not significant. Part worth estimates
revealed that the purity is the most important attribute when selecting a
type of rice.
Findings:

11

Conjoint analysis was used to examine the consumers trade-offs with

respect to rice quality attributes by using ANOVA and part worth score
models. Of the four attributes studied, price was not found to be significant
when making purchasing decisions of rice as it is essential and less price
sensitive commodity. The study revealed that, of the selected quality
attributes, consumers place a high value for purity of than that of the other
attributes. The particular market segment had a high preference for samba
type compared to nadu and raw rice because of its grain size. Even though
there were some consumers who eat red rice owing to health concerns, the
most preferred grain color is found to be white. The preference is not placed
to a single attribute, but it is the interaction of several attributes as tested in
this study.
Questionnaire:
Q1). Age
Q2). Gender
Q3). Profession
Rate the following Mobile Phones on the scale of 1-5(5 being most preferred)
Large screen size: 5 inches or more; Medium screen size: less than 5 inches
but more than 3.5 inches; Small screen size: < 3.5 inches

Ca
rd
ID
1

OS

Screen
Size

Windo
1
ws

Large

2 IOS 7

Small

2
3
4
5

High
Megapixel(12+M
P)
medium
Megapixel(612MP)

Price

20K
+
<10
K

Small

Low Megapixel
(Till 2MP)

<10
K

Symbi
4
an

Small

medium
Megapixel(612MP)

20K
+

Androi
d

Small

Low Megapixel
(Till 2MP)

20K
+

Windo
ws

Camera

12

Symbi
6
an

Small

High
Megapixel(12+M
P)

=10
K20k

Low Megapixel
(Till 2MP)

20K
+
=10
K20k

7 IOS 7

Mediu
m

Androi
8 d

Small

Androi
9 d

Large

1
0

Androi
10 d

Mediu
m

1
1

Windo
11 ws

Small

1
2

Windo
12 ws

Mediu
m

1
3

13 IOS 7

1
4

Low Megapixel
(Till 2MP)
medium
Megapixel(612MP)
High
Megapixel(12+M
P)

<10
K
<10
K
<10
K
=10
K20k

Small

Low Megapixel
(Till 2MP)
medium
Megapixel(612MP)
High
Megapixel(12+M
P)

Symbi
14 an

Large

Low Megapixel
(Till 2MP)

1
5

15 IOS 7

Large

Low Megapixel
(Till 2MP)

<10
K
=10
K20k

1
6

Symbi
16 an

Mediu
m

Low Megapixel
(Till 2MP)

<10
K

<10
K

13

Overall Statistics
Utilities
Utility
Estimate
OS

Windows

-.252

.191

Android

.691

.191

IOS 7

.005

.191

-.445

.191

-.241

.147

.248

.173

-.008

.173

Medium Megapixel
(6-12 Megapixels)

.384

.147

Low Megapixel(Till
2 Megapixels)

-.323

.173

High
Megapixel(>12
Megapixels)

-.061

.173

<10K

.124

.147

=10K-20k

.261

.173

-.385

.173

5.533

.128

Symbian
ScreenSi Small
ze
Medium
Large
Camera

Price

Std.
Error

20K+
(Constant)

14

Importance
Values
OS

32.674

ScreenSi
ze

23.006

Camera

23.950

Price

20.371

Averaged
Importance Score

Correlationsa
Value

Sig.

Pearson's
R

.915

.000

Kendall's
tau

.678

.000

a. Correlations between
observed and estimated
preferences

15

16

17

18

19

20

Conclusion & Limitations

This survey was taken by 121 respondents.
The most important thing to observe is the importance of various attributes.
Clearly OS has the highest importance amongst OS, Screen Size, Camera and
Price
The rest three are quite similar in importance. Respondents have clearly
preferred Android as the most preferred OS followed by IOS 7, Windows and
Symbian. People prefer the Medium screen size as compared to Large or
small. Camera as we know is a useful tool in our Mobile phones and without
any surprise 6-12 megapixels camera were considered most useful followed
by 12+ MP cameras. As it is said that everything comes with a price
somehow respondents understand this fact and have preferred medium cost
phones i.e. 10-20K. More than that has been completely detested.
The most important Limitations of our project was that the respondents
majorly belonged to the students category and were of similar age.

21

References:
1). http://www.sawtoothsoftware.com/download/techpap/undca15.pdf
2).http://www.cybermedia.co.in/corporate/media-room/194385/voice-data-survey-indian-mobilehandsets-market-2012
3). http://qualtrics.com/research-suite/survey-types/conjoint-types/
4). http://bgr.com/2013/07/26/smartphone-market-share-q2-2013-analysis/
5). http://www.researchandmarkets.com/reports/2102641/
6). Research Papers:
Conjoint Analysis and MDS approach to brand improvement of an aerosol
product
Authors: Vincent
centrum Cathedra

Charles, Mukesh Kumar & Tulika Anand, Journal of

The use of Conjoint Analysis to determine consumer buying preferences

Authors: Ernest North and Retha de Vos
Consumer Preferences for Quality Attributes of Rice
Author: B.R. Walisinghe and L.H.P. Gunaratne

22