2. Definition
Conjoint Analysis (kuh n-joint uh-nal-uh-sis):
•“Conjoint analysis is a multivariate technique
developed specifically to understand how
respondents develop preferences for objects
(products, services, or ideas).”
•Source: Hair, Black, Babin, and Anderson (2009)
3. History
• Conjoint analysis grew out of conjoint
measurement in mathematical psychology.
• Green and Rao (1971) and Rao and Wind (1975)
were some of the first academics to use conjoint
analysis in a business context—marketing
research.
• During the 1980s, conjoint analysis gained
widespread acceptance in many industries, with
usage rates increasing up to tenfold.
• By the end of the 1990s, many other disciplines
had adopted conjoint analysis techniques.
• Sources: Hair et. al (2009) and Kuhfeld (2010)
4. Different perspectives and Different
goals
• Buyers want all of the most desirable features at
lowest possible price
• Sellers want to maximize profits by:
1) minimizing costs of providing features
2) providing products that offer greater overall value than the
competition
5. Products/Services are Composed of
Features/Attributes
• Credit Card:
Brand + Interest Rate + Annual Fee + Credit Limit
• On-Line Brokerage:
Brand + Fee + Speed of Transaction + Reliability of Transaction
+ Research/Charting Options
6. Company’s objective
• How our product or services compares to our
competitors and how we can best optimise
the value we give to the customer?
• By Conjoint analysis:
•
we can give up the total value or utility
value our product is giving the customer and
compare it to the value for the competition.
7. Requirements for successful conjoint
analysis
• Defining the total utility of the object
• All attributes that potentially create or detract
from the overall utility of the product or
service should be included.
• Specifying the determinant factors
• include the factors that best differentiate
between the objects.
8. Assumptions of conjoint analysis
• The product is a bundle of attributes.
• Utility of a product is a simple function of the
Utility of attributes.
• Utility predicts behaviour.
9. How Does Conjoint Analysis Work?
• We vary the product features (independent variables) to build many
(usually 12 or more) product concepts
• We ask respondents to rate/rank those product concepts
(dependent variable)
• Based on the respondents’ evaluations of the product concepts, we
figure out how much unique value (utility) each of the features
added
• (Regress dependent variable on independent variables; betas equal
part worth utilities.)
10. Rules for Formulating
Attribute Levels
• Don’t include too many levels for any one attribute
– The usual number is about 3 to 5 levels per attribute
– The temptation (for example) is to include many, many
levels of price, so we can estimate people’s preferences for
each
– But, you spread your precious observations across more
parameters to be estimated, resulting in noisier (less
precise) measurement of ALL price levels
– Better approach usually is to interpolate between fewer
more precisely measured levels for “not asked about”
prices
11. Rules for Formulating
Attribute Levels
• Whenever possible, try to balance the number of levels across
attributes
• There is a well-known bias in conjoint analysis called the “Number
of Levels Effect”
– Holding all else constant, attributes defined on more levels
than others will be biased upwards in importance
– For example, price defined as ($10, $12, $14, $16, $18, $20)
will receive higher relative importance than when defined as
($10, $15, $20) even though the same range was measured
– The Number of Levels effect holds for quantitative (e.g.
price, speed) and categorical (e.g. brand, color) attributes
12. Rules for Formulating
Attribute Levels
• Make sure levels from your attributes can combine freely with
one another without resulting in utterly impossible
combinations (very unlikely combinations OK)
– Resist temptation to make attribute prohibitions
(prohibiting levels from one attribute from occurring with
levels from other attributes)!
– Respondents can imagine many possibilities (and evaluate
them consistently) that the study commissioner doesn’t
plan to/can’t offer. By avoiding prohibitions, we usually
improve the estimates of the combinations that we will
actually focus on.
– But, for advanced analysts, some prohibitions are OK, and
even helpful
29. •
ACA
•
•
•
Adaptive Conjoint Analysis is a hybrid conjoint approach in that it uses
both analysis of product combinations (combinations of factor levels) as well
as self-reported importance information to derive utilities.
•
Three components of analysis:
•
•
•
-Factor ratings (preferability)
-Rank order of levels within factors
-Graded comparisons of partial product combinations
•
•
•
•
-It allows for a larger number of factors and levels can be analyzed.
-Can only be administered via computer.
-Cannot analyze interactions.
-Price elasticity still an issue.
34. •
CBC
•
CBC, or Choice Based Conjoint, has become the preferred method, due to
it’s ability to truly gauge price elasticity, and it’s easy to comprehend tradeoff task.
•
Full product combinations are pitted against each other in “choice sets”.
Respondents choose among the products depicted, or (as an option) can
choose none of the products.
•
A respondent typically receives anywhere from 10 to 20 choice sets,
depending on the number of factors and levels in the design.
•
•
•
•
•
-It’s modeling capabilities (interactions, special effects, etc.) are seen as an
improvement from prior methods.
-Due to relative pricing, elasticity models are more accurate.
-Like ACA, allows for more factors and levels than traditional method.
-Individual utilities now available (first versions generated aggregate
models)
36. Strengths of CBC
• Questions closely mimic what buyers do in real world: choose
from available products
• Can investigate interactions, alternative-specific effects
• Can include “None” alternative, or multiple “constant
alternatives”
• Paper or Computer/Web based interviews possible
37. Weaknesses of CBC
• Usually requires larger sample sizes than with CVA or ACA
• Tasks are more complex, so respondents can process fewer
attributes (CBC recommended <=6)
• Complex tasks may encourage response simplification
strategies
• Analysis more complex than with CVA or ACA