Browse list of available series in The Marketing & Management Collection
Review purchasing information
Recommend The Marketing & Management Collection to your librarian
Request to be kept updated on The Marketing & Management Collection
View all talks & series with full access

Guest (sample access)

Optional Login with Username


        
> Home  /  Marketing & Management  /  Series  /  Bayesian Analysis in Marketing  /  Talk Details
SHARE:   Email via Outlook   Email via Web   Facebook   Twitter   |   more
Close SHARE
Please select one of the methods below to share the following page with your collegues:
The value of HB in conjoint/choice analysis
Blogger Google Reader
Delicious Linked In
Digg MySpace
Favorites PDF Online
Gmail

Hello. As a guest, you do not have full access to this talk. Click the PLAY button below to watch the sample extract. For increased access, you may login or click on "Obtain Full Talk Access" below.


Printable Slide
Handouts PDF
The value of HB in conjoint/choice analysis - play sample talk extract

    SPEAKER(S)

Mr. Bryan K. Orme - President, Sawtooth Software, Inc., USA

Bryan received his BA from Brigham Young University and an MBA from the University of Texas at Austin. Prior to joining Sawtooth Software, Bryan worked in the marketing sciences department at IntelliQuest, Inc. He has published many articles on conjoint analysis and received the David K. Hardin award for the best paper published in Marketing Research in 2004. Bryan is the author of Getting Started with Conjoint Analysis and has also authored numerous Sawtooth Software technical papers and manuals. Bryan has been active at the American Marketing Association's Advanced Research Techniques Forum. He was twice the co-recipient of their Best Presentation award, has served on the Program Committee in 2002 and chaired their event in 2003.

Talk Online Publication: Jan 2010

TOPICS COVERED IN THE VALUE OF HB IN CONJOINT/CHOICE ANALYSIS

Introduction to conjoint/choice analysis - How HB has improved ratings-based conjoint methods - Why HB has particularly benefited choice-based models - Market simulation issues including IIA - Practical considerations such as utility constraints and using proper priors

How to cite this talk:
Orme, B.K. (2010), "The value of HB in conjoint/choice analysis", in Allenby, G.M. and Rossi, P.E. (eds), Bayesian Analysis in Marketing: A breakthrough in customer analytics, The Marketing & Management Collection, Henry Stewart Talks Ltd, London (online at http://hstalks.com/go)

Direct talk access link:
http://hstalks.com/lib.php?t=HST99.2266_1_2&c=250

    DETAILED SLIDE INDEX

1. Introduction
2. Agenda
3. Conjoint/choice analysis: essential background
4. Practical applications
5. Individual-level vs. aggregate analysis
6. Overfitting and conjoint analysis
7. A two-week part-worth estimation program
8. Early papers
9. Why did HB work for ratings-based conjoint?
10. Improvement for ratings-based conjoint
11. Analysis of choice data
12. IIA
13. Example of IIA
14. IIA and levels of aggregation
15. How does HB reduce IIA problems? (1)
16. How does HB reduce IIA problems? (2)
17. What about interaction effects?
18. What about distributions?
19. Why did HB work for choice-based conjoint?
20. Revolutionary benefit for choice-based conjoint
21. Draws
22. Useful methods of market simulation
23. Draws vs. RFC
24. Why do we care about tuning for scale
25. Shrinkage
26. Problems with shrinkage
27. Covariates in HB
28. Monotonicity constraints (utility constraints)
29. Operationalizing constraints
30. To constrain or not to constrain
31. Uninformative priors?
32. Coding categorical attributes
33. Problems in the posteriors
34. Solutions
35. Dummy coding
36. Effects coding
37. Thank you
38. END