HOORCOLLEGE 1: INTRODUCTION
WHAT IS CONJOINT ANALYSIS
Conjoint Analysis is a survey-based technique that allows the analyst to understand people’s preferences for a
product/service/brand etc. and especially the trade-offs they make in making choices.
WHY CONJOINT ANALYSIS
1. In direct surveys, respondents might say they consider all attributes important → this is not
informative → don’t force trade-offs.
2. Conjoint enforces trade-offs between attributes as in real purchase occasions
3. Conjoint reduces problem of socially desirable answers
4. Conjoint adds realism → people evaluate product, not isolated attributes
5. Conjoint analysis is straightforward → suitable software available
WHY SHOULD WE RUN HYPOTHETICAL EXPRERIMENTS IF FIRMS CAN INCREASINGLY MAKE USE
OF LARGE AMOUNTS OF TRANSACTIONAL PURCHASE DATA?
1. Lack of experimental price variations required to learn consumers’ preferences
2. Conjoint allows to measure consumer preferences for product or attribute levels not yet introduced in
the marketplace → you don’t have transactional data
a. Especially relevant for e.g. pricing of new product innovations
FIELD EXPERIMENTS ARE PROMINENT ALTERNATIVES FOR THE GOAL OF LEARNING CONSUMER
PREFERENCES. HOWEVER…
1. Often, field experiments are difficult to conduct and not feasible in high ticket product categories
(like cars, laptops, etc. → products which are not frequently purchased)
2. Field experiments are limited to products already existing in the marketplace.
1. CONJOINT DESIGN
1. Raking-based conjoint:
o Choose the most-preferred product, then the second most-preferred product, … until the
least-preferred product
2. Rating-based conjoint:
o Give a score to each product in turn
3. Choice-based conjoint:
o Choice between different variants
o Choose the most-preferred product only
2. RATING-BASED CONJOINT (DISADVANTAGES)
1. Not realistic
a. In real-life, we buy product rather than rating them
2. Not clear whether spread in ratings is due to real preferences or due to response style
3. Implications for sales levels and market shares are not clear
a. Sales and shares result from consumer choices, not ratings
4. Why don’t we ask the respondents to choose a product directly, rather than asking them to rate
products?
,3. CHOICE-BASED CONJOINT
In choice-based conjoint we record the choices made by every customer during the n tasks (i.e. choice sets).
Because, in every choice set, a different combination of attribute levels is used, we can derive the effect of
different combinations of attribute levels on choice (preferences = attribute part-worths). As we repeat the
conjoint exercise across many customers, we can also detect whether different customers have different
preferences (customer-specific preferences).
ADVANTAGES OF CHOICE-BASED CONJOINT
1. Tradeoffs are enforced even more
2. Realistic: the choice-setting mimics real-life
3. Accommodates no-choice option (→ sales proxy)
a. None of the offered alternatives is attractive
b. I would stick to my current product
4. Avoids the need of ad-hoc rules to predict market shares
5. No subjective scaling
6. Choice is cognitively less demanding than ratings
DISADVANTAGES OF CHOICE-BASED CONJOINT
1. Hypothetical bias: respondents’ product choices (potentially at very large prices) might be influenced
by the experimental setting, i.e. with no consequences for actual purchase behaviour in real world
2. Small individual level data: respondents become fatigue if exposed to a large number of choice tasks
that are actually required if the experiment includes large numbers of attribute levels
3. Bayesian methods and prior specifications: Bayesian statistical methods help as they efficiently pool
information across respondents (shrinkage). However, some analysts regard the inclusion and
specification of priors as subjective.
2. CONJOINT ANALYSIS
1. Logit (Logistic Regression)
a. Aggregate level (same part-worths for all respondents)
– assuming same preferences may give misleading results
+ high precision, as all respondents are combined
What if you prefer the freedom of an Android while I Like the synchronization feature of the iPhone
2. Latent-class (LCA)
a. Segment level (different part-worths for different segments)
+ Realistic, as segments take into account different preferences
+ High precision if all respondents are used in one big analysis
3. Hierarchical Bayes (HB)
a. Individual level (different part-worths for each respondent)
+ Realistic, as respondents have different preferences
+ High precision thanks to the joint estimation
- How many strategies should the firm implement given the diversity of preferences?
, 3. MARKET SIMULATIONS
Competitive market scenarios to predict which product respondents would choose
• What can the choice simulator do?
o Lets you predict which SKU respondents or segments of the population will choose (estimate
demand and market share)
o Lets you play ‘what-if’ games to investigate the value of modifications to an existing product
or alternative
o Lets you investigate product line extensions
WHAT IS CONJOINT ANALYSIS
Conjoint Analysis is a survey-based technique that allows the analyst to understand people’s preferences for a
product/service/brand etc. and especially the trade-offs they make in making choices.
WHY CONJOINT ANALYSIS
1. In direct surveys, respondents might say they consider all attributes important → this is not
informative → don’t force trade-offs.
2. Conjoint enforces trade-offs between attributes as in real purchase occasions
3. Conjoint reduces problem of socially desirable answers
4. Conjoint adds realism → people evaluate product, not isolated attributes
5. Conjoint analysis is straightforward → suitable software available
WHY SHOULD WE RUN HYPOTHETICAL EXPRERIMENTS IF FIRMS CAN INCREASINGLY MAKE USE
OF LARGE AMOUNTS OF TRANSACTIONAL PURCHASE DATA?
1. Lack of experimental price variations required to learn consumers’ preferences
2. Conjoint allows to measure consumer preferences for product or attribute levels not yet introduced in
the marketplace → you don’t have transactional data
a. Especially relevant for e.g. pricing of new product innovations
FIELD EXPERIMENTS ARE PROMINENT ALTERNATIVES FOR THE GOAL OF LEARNING CONSUMER
PREFERENCES. HOWEVER…
1. Often, field experiments are difficult to conduct and not feasible in high ticket product categories
(like cars, laptops, etc. → products which are not frequently purchased)
2. Field experiments are limited to products already existing in the marketplace.
1. CONJOINT DESIGN
1. Raking-based conjoint:
o Choose the most-preferred product, then the second most-preferred product, … until the
least-preferred product
2. Rating-based conjoint:
o Give a score to each product in turn
3. Choice-based conjoint:
o Choice between different variants
o Choose the most-preferred product only
2. RATING-BASED CONJOINT (DISADVANTAGES)
1. Not realistic
a. In real-life, we buy product rather than rating them
2. Not clear whether spread in ratings is due to real preferences or due to response style
3. Implications for sales levels and market shares are not clear
a. Sales and shares result from consumer choices, not ratings
4. Why don’t we ask the respondents to choose a product directly, rather than asking them to rate
products?
,3. CHOICE-BASED CONJOINT
In choice-based conjoint we record the choices made by every customer during the n tasks (i.e. choice sets).
Because, in every choice set, a different combination of attribute levels is used, we can derive the effect of
different combinations of attribute levels on choice (preferences = attribute part-worths). As we repeat the
conjoint exercise across many customers, we can also detect whether different customers have different
preferences (customer-specific preferences).
ADVANTAGES OF CHOICE-BASED CONJOINT
1. Tradeoffs are enforced even more
2. Realistic: the choice-setting mimics real-life
3. Accommodates no-choice option (→ sales proxy)
a. None of the offered alternatives is attractive
b. I would stick to my current product
4. Avoids the need of ad-hoc rules to predict market shares
5. No subjective scaling
6. Choice is cognitively less demanding than ratings
DISADVANTAGES OF CHOICE-BASED CONJOINT
1. Hypothetical bias: respondents’ product choices (potentially at very large prices) might be influenced
by the experimental setting, i.e. with no consequences for actual purchase behaviour in real world
2. Small individual level data: respondents become fatigue if exposed to a large number of choice tasks
that are actually required if the experiment includes large numbers of attribute levels
3. Bayesian methods and prior specifications: Bayesian statistical methods help as they efficiently pool
information across respondents (shrinkage). However, some analysts regard the inclusion and
specification of priors as subjective.
2. CONJOINT ANALYSIS
1. Logit (Logistic Regression)
a. Aggregate level (same part-worths for all respondents)
– assuming same preferences may give misleading results
+ high precision, as all respondents are combined
What if you prefer the freedom of an Android while I Like the synchronization feature of the iPhone
2. Latent-class (LCA)
a. Segment level (different part-worths for different segments)
+ Realistic, as segments take into account different preferences
+ High precision if all respondents are used in one big analysis
3. Hierarchical Bayes (HB)
a. Individual level (different part-worths for each respondent)
+ Realistic, as respondents have different preferences
+ High precision thanks to the joint estimation
- How many strategies should the firm implement given the diversity of preferences?
, 3. MARKET SIMULATIONS
Competitive market scenarios to predict which product respondents would choose
• What can the choice simulator do?
o Lets you predict which SKU respondents or segments of the population will choose (estimate
demand and market share)
o Lets you play ‘what-if’ games to investigate the value of modifications to an existing product
or alternative
o Lets you investigate product line extensions
