TCA/HB Compared to CBC/HB for Predicting Choices Among Multi-Attributed Products
PBN-AR
Instytucja
Filia w Jeleniej Górze (Uniwersytet Ekonomiczny we Wrocławiu)
Informacje podstawowe
Główny język publikacji
en
Czasopismo
Archives of Data Science Series A
ISSN
2363-9881
EISSN
Wydawca
KIT Scientific Publishing
DOI
URL
Rok publikacji
2014
Numer zeszytu
1
Strony od-do
1-11
Numer tomu
1
Identyfikator DOI
Liczba arkuszy
0.5
Autorzy
(liczba autorów: 4)
Pozostali autorzy
+ 2
Streszczenia
Język
en
Treść
For some years, choice-based conjoint analysis (CBC) has demonstrated its superiority over other preference measurement alternatives. So, e.g., in a recent study on German and Polish cola consumers, the superiority of CBC over traditional conjoint analysis (TCA) was striking. As one reason for this superiority, the usage of hierarchical Bayes for CBC parameter estimation was mentioned (CBC/HB). This paper clarifies whether this really makes the difference: Hierarchical Bayes is also used for TCA parameter estimation (TCA/HB). The application to the above mentioned data shows, that this improves the predictive validity compared to TCA but is still inferior to CBC/HB in “high data quality cases”. However, in “low data quality cases” TCA/HB is superior to CBC/HB.
Inne
System-identifier
WUT0e84162e49274e84b2d66ccb51806dd4