Choice-Based Conjoint (CBC) Workshop
by Greg Allenby, Joachim Büschken, Peter Kurz and Winfried Steiner
The workshop is cancelled due to the actual CORVID-19 situation.
Haus der bayerischen Landwirtschaft Herrsching
New dates will be announced as soon as possible!
Rieder Str. 70, 82211 Herrsching am Ammersee
|Start:||Monday,||03 August 2020||09:00|
|End:||Thursday,||06 August 2020||16:00|
This four days workshop teaches participants advanced topics in Bayesian estimation of part-worth utilities from Choice Based Conjoint excercises.
Days 1 and 2 provide advanced knowledge to modern Bayesian statistics in marketing and how Bayesian estimation techniques work.
Software algorithms from the R contributed package "bayesm" will be used to illustrate the methods.
Day 3 is planned as a colloquium. It provides participants with the opportunity to present their own (dissertation) research and to discuss possible
approaches with the other participants and the instructors to answer the research questions. Alternatively or additionally, case studies are discussed
how to use bayesian techniques for concrete problem settings.
Day 4 is an additional day dealing with Bayesian experimental desigs for choice models (Software examples with the R-package "idefix" will be used to illustrate the designs) and portfolio optimization based on estimation results from choice based conjoint studies.
The workshop will adress all pressing questions concerning utility estimation from CBC studies and give deeper insight in experimental designs, including:
- Understanding Bayesian inference
- Basics of random utility models
- Markov-Chain Monte Carlo methods
- The hierachical multinominal logit
- Upper level model- lower level model
- Posterior draws
- Checking convergence
- Using informative priors
- Willingness to pay
- Incorporating other informations about respondents
- Advanced experimental design strategies for individual choice estimation
- Portfolio optimization based on part-worth utilities from CBC models