L11 - Conjoint measurement analysis Flashcards
Goal of the conjoint measurement analysis
Identify and measure the attributes and attribute levels that people care most about ( that have the strongest impact on preferences)
–> decompositional method
What is the principle of the conjoint analysis?
Create options presenting combinations of different attribute levels and measure the preferences for different options; then infer the influence of the different attributes and attribute levels.
Example conjoint analysis
Estimating the influence of individual product features on preferences.
What are the steps in the conjoint measurement analysis?
3 key assumptions of conjoint analysis
- preference is based on a combination of all attributes (they are CONsidered JOINTly)
- attributes can compensate each other
- the attributes are independent
Is relevance important when selecting the attributes?
Yes. The attribute must be relevant for people’s preferences (-> identification of attributes using focus groups)
Is control important when selecting the attributes?
Only choose attributes and levels that can be modified and realized during product design.
Is independence important when selecting attributes?
Yes the attributes should be independent.
Is compensatory important when selecting the attribute?
Yes. The attributes can compensate each other (e.g. a reduction of the calorie content can be compensated by an improvement in taste)
Is an exclusion criteria allowed when selecting attributes?
No. The attribute levels should not be exclusion criteria (“knock-off criteria”).
Do the number of attributes and attribute levels have to be limited?
Yes.
How to calculate the number of profiles?
What is a full factorial design?
When you list all the profiles (combinations of attributes and attribute levels). This can result in too many options for the customer.
How can you reduce the number of combinations of the profiles?
Fractional design with latin square. -> You can maximize information without considering every option.
What is the criteria you have to fulfill so that you can apply the fractional design?
Only if no interaction between the attributes is to be expected.
What is the latin square restricted to?
Situations with 3 attributes and 3 levels.
What is the principle of the latin square?
Each attribute level is combined once with each other attribute levels of the other attributes.
What is another fractional design method?
Orthogonal design?
When do you use the orthogonal design?
When you have more than 3 attributes and levels.
What is the assumption of the orthogonal design?
That no interactions between attributes are to be expected.
What is the goal of the orthogonal design?
That the attributes are uncorrelated. It is based on a simulation methods.
Ordinal methods for preference assessment
Metric methods for preference assessment
What is the ranking method?
Please rank the 9 options according to how attractive you find them.
