lecture9conjointanalysis-110607121417-phpapp01.pdf
- 1. CONJOINT ANALYSIS Prof Narayan Janakiraman
- 2. Customer Value Assessment Procedures Customer Value Attitude-Based Direct Questions Unconstrained Constrained/Compositional Methods Multiattribute value analysis Indirect/(Decompositional Methods) Conjoint analysis Behavior-Based Inferential/Value-Based
- 3. Conjoint Analysis and Concept Testing Concept testing Show one product concept and get overall “Purchase Intent” feedback Also get product diagnostics Conjoint Analysis Show multiple concepts and ask for overall preference Concepts differ on Attributes and levels within an attribute Based on overall preference get “part-worths” for attributes and levels within an attribute
- 4. A Survey Familiarity & usage of value assessment methods 58 industrial firms in the top 125 of the Fortune 500 list 16 market research firms from the top 40
- 5. Survey Results Method Industrial Market Research Familiarity % Usage % Familiarity % Usage % Internal Engg. Assessment 61.3 42.5 - - Field value-in-use 63.8 36.3 25 5 Focus group 92.5 60 90 60 Direct survey 91.3 48.8 85 55 Benchmarks 83.8 27.5 80 25 Conjoint 75 28.8 90 60 Compositional methods 45 10 40 5
- 6. Conjoint Analysis in Product Design Should we offer our business travelers more room space or a fax machine in their room? Given a target cost for a product, should we enhance product reliability or its performance? Should we use a steel or aluminum casing to increase customer preference for the new equipment?
- 7. P&G and Disposable Diapers Question: What value do consumers associate with two improved features in disposable diapers: Improved absorbency Elastic waistband
- 8. Conjoint Analysis Assumption Products can be defined by their individual attributes and levels within the attribute Consumer responses to the overall preference can be then partitioned to attributes
- 10. Eg. Packaged Soup individual concept
- 11. Eg. Packaged Soup Conjoint INPUT Cards and Ratings
- 12. Eg. Packaged Soup Conjoint OUPUT 1 Part Worths
- 13. Eg. Packaged Soup Conjoint OUPUT 1 Part Worths
- 14. Weights of Attributes Flavor 45% Calories 25% Salt Freeness 22% Price 8% Eg. Packaged Soup Conjoint OUPUT 2 Importance
- 15. How were the part-worths calculated and how was the importance determined? How does one use Part Worths? Importance? The Black box
- 16. The Conjoint Model attributes utilities a u a u U ... ) ( ) ( 2 1
- 17. Notebook computer example Processing speed: 1.5 GHz or 2.5 GHz 2) Hard drive: 120 GB or 160 GB 3) Memory: 1 GB or 2 GB RAM There are 8 different combinations of notebook - defined as product profiles:
- 19. Input to computer system – dummy variable regression
- 20. Part Worth Estimation Regression of ranks vs the attributes U = a + b1*Processor + b2*Hard Drive + b3*Memory U1 a b1 0 b2 0 b3 0 a U2 a b1 1 b2 0 b3 0 a b1 U3 a b1 0 b2 1 b3 0 a b2 U4 a b1 0 b2 0 b3 1 a b3 a U1 1 b1 U2 U1 5 1 4 b2 U3 U1 3 1 2 b3 U4 U1 2 1 1 The intution
- 21. Forecast preferences to check accuracy 8 1 1 1 6 1 0 1 4 1 1 0 7 0 1 1 3 2 1 8 3 2 1 7 3 2 1 6 3 2 1 5 b b b a U b b b a U b b b a U b b b a U
- 22. Weightage and Relative Importance of Each Attribute 7 4 3 2 1 1 b b b b b2 b1 b2 b3 2 7 b3 b1 b2 b3 1 7 Processo r Speed Hard Drive Memory = 57% = 29% = 14%
- 23. Segment consumers based on preferences Are there segments in terms of preferences? Here preference is the “basis” and “age” could be the descriptor
- 24. Eg. Packaged Soup Which is the most important attribute & which is the best product to introduce?
- 25. Conjoint Simulation - The Motivation 1. What share can the new brand obtain? 2. Where does this share will come from?
- 26. Conjoint Simulation - The Principle Before introduction share: A=40%, B=60%. After introduction share: A=20%,B=50%, and New=30%.
- 27. Other ways of getting responses
- 28. Stage 1—Design the conjoint study: Step 1.1: Select attributes relevant to the product or service category, Step 1.2: Select levels for each attribute, and Step 1.3: Develop the product bundles to be evaluated. Stage 2—Obtain data from a sample of respondents: Step 2.1: Design a data-collection procedure, and Step 2.2: Select a computation method for obtaining part-worth functions. Stage 3—Evaluate product design options: Step 3.1: Segment customers based on their part-worth functions, Step 3.2: Design market simulations, and Step 3.3: Select choice rule. Conjoint Study Process
- 29. 29 Attributes Should Be… Determinant Easily measured and communicated Controllable by the company Realistic Such that there will be preferences for some levels over others Compensatory As a set, sufficient to define the choice situation Without built-in redundancies
- 30. 30 How Many Levels per Attribute? Levels and range should be meaningful, informative, and realistic to consumers and producers Avoiding absurd configurations Marginal increases in levels can greatly increase respondent’s task
- 31. 31 Which Data Collection Method? Full profile: Show complete list of attributes Limited to 6-7 attributes Pair-wise: Show pairs of attributes in matrix; each cell rated from most to least preferred Lacks realism Inconsistent responses likely
- 32. Designing a Frozen Pizza – Paired Comparison Approach 1. Crust 2. Type of Cheese 3. Price Pan Romano $ 9.99 Thin Mixed cheese $ 8.99 Thick Mozzeralla $ 7.99 4. Topping 5. Amount of Cheese Pineapple 2 oz. Veggie 4 oz. Sausage 6 oz. Pepperoni A total of 324 (3 * 4 * 3 * 3 * 3) different pizzas can be developed from these options!