Samenvatting
Conjoint Analysis Summary - 2023/2024 - All lectures & tutorials + notes
- Instelling
- Tilburg University (UVT)
Includes all lectures and tutorials including notes from Conjoint Analysis 2023/2024
[Meer zien]Voorbeeld 4 van de 52 pagina's
Voorbeeld 4 van de 52 pagina's
In winkelwagengesponsord bericht van onze partner
Voorbeeld van de inhoud
WEEK 1Lecture 1
Conjoint Analysis
Products are represented as bundles of attributes. Levels of each attribute de ne the product.
Conjoint analysis is a survey-based technique that allows the analyst to understand people’s
preferences for a [product/service/brand/medical treatment/job/course] and especially the
trade-offs they make in making choices.
Why use conjoint analysis?
- In direct surveys, respondents might say they consider all attributes important.
o Not informative.
o Conjoint lets people make choices and learn from the outcomes of these
choices.
- Conjoint enforces trade-offs between attributes as in real purchase occasion.
o All attributed evaluated at once.
o Respondents evaluate “complete” products with both strong and weak
attributes.
- Conjoint reduces problem of socially desirable answers.
o People are not stating an opinion, they are just choosing products. Helps with
sensitive topics.
- Conjoint adds realism.
o In real-life, consumers evaluate products, not isolated attributes (do they
consciously know which attributes matter?)
- Conjoint analysis is straightforward.
o Suitable software is available (Sawtooth).
Conjoint in the age of big data
Why should we run hypothetical choice experiments if rms can increasingly make use of
large amounts of transactional purchase data?
1. Lack of experimental price variations required to learn consumers’ preferences. In the
real world (company data sets), there may not be a lot of variation in for example
price. In an experiment, you can manipulate this price and see how consumers react.
2. Conjoint allows to measure consumer preferences for products or attribute levels not
yet introduced in the marketplace.
3. 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, eld experiments are dif cult to conduct and not feasible in high-ticket product
categories (like laptops, cars). Field experiments have their costs of implementing.
E.g., a car dealer would not offer its car at 30% off.
2. Field experiments are limited to products already existing in the marketplace.
,Application:
- Economics
o Evaluate transportation alternatives.
o Compare energy alternatives.
o Measure environmental impact.
- Law
o Measure effects of litigation.
o Damage assessment.
o Identify boundaries between rms.
o Evaluate punishment alternatives.
o Select jury members.
- Human resources
o Screen potential employees.
o Design compensation packages.
o Select health care plans.
o Evaluate performance.
o Predict employee responses.
Ranking-based conjoint: choose the most-preferred product, then the second most-
preferred product, until the last-preferred product.
Rating-based conjoint: give a score to each product in turn.
- Not realistic.
o In real life, we buy products rather than rating them.
- Not clear whether spread in ratings is due to real preferences or due to response
style.
o E.g., small spread: does this mean the respondent has weak preferences or
gives cautious answers?
- Implications for sales levels and market shares are not clear.
o Sales and shares result come from consumer choices, not ratings.
o What would be the rating threshold?
Choice-based conjoint: choice between different variants. Choose the most-preferred
product only.
- 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.
o Preference = attribute part-worths.
- As we repeat the conjoint exercise across many customers, we can also detect
whether different consumers have different preferences.
o Customer-speci c preferences.
Advantages of choice-based conjoint:
- Trade-offs are enforced even more.
- Realistic: the choice-setting mimics real-life.
- Accommodates no-choice option (“none of the offered alternatives is attractive”, “I
would stick to my current product”) --> sales proxy: what will your sales/market share
be?
, - Avoids the need of ad-hoc rules to predict market shares.
- No subjective scaling.
- Choice is cognitively less demanding than ratings.
Disadvantages of choice-based conjoint:
- 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 the real world. A solution to this would be to give the
respondent a budget. However, if you would give a budget to your respondents, it is
(1) expensive and (2) logistically dif cult.
- 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.
- Bayesian methods and prior speci cations: Bayesian statistical methods help as
they ef ciently pool information across respondents (shrinkage) (e.g., dividing
respondents into groups). However, some analysts regard the inclusions and
speci cations as subjective.
Logistic regression
DV = product chosen or not
IV = product attributes
DV = logit (IV)
e.g., choice = f(price, quality, colour, speed, discount)
What if taste differ? Use latent-class and hierarchical Bayes.
- Aggregate level (same part-worths for all respondents)
o Assuming same preferences may give misleading results (-).
o High precision, as all respondents are combined (+).
o Method of analysis: logit.
- Segment level (different part-worths for different segments)
o Realistic, as segments take into account different preferences (+).
o High precision if all respondents are used in one big analysis (+).
o Heterogeneity within segments is not taken into account (-).
o Method of analysis: latent class analysis.
- Individual level (different part-worths for each respondent)
o Realistic, as respondents have different preferences (+).
o High precision thanks to the joint estimation (+).
o How many strategies should the rm implement given the diversity of
preferences (-)?
o Method of analysis: hierarchical bayes (HB).
Market simulations: competitive market scenarios to predict which products respondents
would choose. What are the market shares after introducing a new product or changing the
consumer price? A choice simulator can:
- Let you predict which SKU respondents or segments of the populations will choose
(estimate demand and market share).
, - Lets you play “what-if” games to investigate the value of modi cations to an existing
product or alternative.
- Lets you investigate product line extensions.
Random utility theory – decompositional view of conjoint
Decompositional view:
Product (stimulus)
Product’s attribute
Attribute’s level
We decompose a product into the sum of its attribute levels and want to estimate consumers’
preferences (utilities) for the different levels.
The utility of a stimulus = the sum of the utilities of the various attributes’ levels.
You can compare total utilities across products and the consumer will choose the product
with the highest utility.
In general, customers pick the stimulus with the highest utility, i.e., consumers are assumed to
be rational utility-maximizing agents.
Random utility theory
- A consumer generally chooses the alternative that she likes the most, subject to
constraints such as income, category budget, and time.
- However, beside “observable” attribute levels, there are other “unobservable” factors
that influence consumer’s choice.
- Example (if only attribute levels matter for choice):
o Choose Fiat if (Utility Fiat 500 > Utility Skoda Octavia)
o That is, everything else equal, if:
o [U(brand = Fiat) + U(trunk size = <300L) > [U(brand = Skoda) + U(trunk size =
> 500L)
- Sometimes, a customer does not choose the stimulus with the highest observable
utility.
o Other factors, unobservable to the researcher, might also influence choice.
- Unobservable, true utility = observable & systematic utility + random
component.
o Random component can be tiredness, uncertainty, distraction, context, etc.
o E.g., context effect could be the compromise effect (choosing the middle
option as people don’t want to make extreme choices).
- Let C be a choice set composed of n stimuli (e.g., products).
- The probability of choosing stimulus i among the choice set C is equal to:
o P(i|C) = P[Ui > Uj], for all j ∈ C.
Ui = utility of stimulus i.
Uj = utility of stimulus j.
- The utility of stimulus i is the sum of all the utilities of all attributes xi and some random
noise εi.
o Ui = β1xi1 + β2xi2 + … + βkxik + εi
Voordelen van het kopen van samenvattingen bij Stuvia op een rij:
Verzekerd van kwaliteit door reviews
Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!
Snel en makkelijk kopen
Je betaalt supersnel en eenmalig met iDeal, creditcard of Stuvia-tegoed voor de samenvatting. Zonder lidmaatschap.
Focus op de essentie
Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!
Veelgestelde vragen
Wat krijg ik als ik dit document koop?
Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.
Tevredenheidsgarantie: hoe werkt dat?
Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.
Van wie koop ik deze samenvatting?
Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper BAstudent1. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €7,16. Je zit daarna nergens aan vast.
Is Stuvia te vertrouwen?
4,6 sterren op Google & Trustpilot (+1000 reviews)
Afgelopen 30 dagen zijn er 53920 samenvattingen verkocht
Opgericht in 2010, al 14 jaar dé plek om samenvattingen te kopen