The confounding of effects in rank-based conjoint-analysis

Basic confounding patterns for full-profile conjoint analyses based upon ranking are examined. It is shown that commonly used orthogonal main-effect designs can lead to biased part-worth estimates, especially to an underestimation of less important variables. An alternative design procedure is developed to overcome this flaw. The model is tested by means of simulation analyses and is applied to a marketing research study. Some guidelines for applications are provided.

MoreLess

Year of publication:	1996
Authors:	Teichert, Thorsten Andreas
Publisher:	Kiel : Universität Kiel, Institut für Betriebswirtschaftslehre
Subject:	Marktforschung \| Conjoint-Analyse \| Clusteranalyse \| Theorie

More details

Series:	Manuskripte aus den Instituten für Betriebswirtschaftslehre der Universität Kiel ; 409
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	1003521401 [GVK] hdl:10419/149040 [Handle] RePEc:zbw:cauman:409 [RePEc]
Source:	EconStor

Persistent link: https://ebvufind01.dmz1.zbw.eu/10011583000