Conjoint measurement en Fishbeins theory of reasoned action (on)geldige aannames bij attitudeonderzoek

Janssen, P.J.R. (2012) Conjoint measurement en Fishbeins theory of reasoned action (on)geldige aannames bij attitudeonderzoek.

[img]
Preview
PDF
401kB
Abstract:Assumptions limit what can be measured. They have to be valid for the variable that is being measured. With Conjoint Measurement, the validity of assumptions that are made when using certain measurement methods can be tested. The expectancy value part of the Theory of Reasoned Action (TRA) will be tested in this manner. Additivity and independence of attributes are assumed within the TRA. A model for choice between objects can be derived, and its assumptions can be tested. The question is: does the model hold? Twenty-five subjects compared eight holidays side by side (in stead of scoring every attribute seperately), each time preferring one of the two. The attributes of the objects were represented in the choice situation. The method of analysis is not a statistical one: The choices of each person are tested on applicability on the model that is presumed by the TRA, which assumes additivity and independence of objects. For thirteen subjects, the model holds. Two subjects clearly do not fit the model. There is no conclusion to draw about the remaining ten subjects. No systematic disorders have been found. These conclusions only valid for the tested attributes. Research methods like the Likert scale asssume additivity and independence of attributes. For one to be sure what is being measured with this kind of method, these assumptions have to be tested per subject in order to know if the variables meet the assumptions.
Item Type:Essay (Bachelor)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:77 psychology
Programme:Psychology BSc (56604)
Link to this item:http://purl.utwente.nl/essays/62361
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page