Scaling Distortion in Numerical Conjoint Measurement
Open Access
- 1 April 1984
- journal article
- Published by SAGE Publications in Applied Psychological Measurement
- Vol. 8 (2), 183-198
- https://doi.org/10.1177/014662168400800207
Abstract
Proponents of numerical conjoint measurement gen erally assume that the technique's goodness-of-fit mea sure will detect an inappropriate composition rule or the presence of random response error. In this paper a number of hypothetical and real preference rank order ings are analyzed using both axiomatic conjoint mea surement and numerical conjoint measurement to dem onstrate that this assumption is not warranted and may result in a distorted scaling.Keywords
This publication has 27 references indexed in Scilit:
- Importance of measurement theory, error theory, and experimental design for testing the significance of interactions.Psychological Bulletin, 1980
- Robustness of Conjoint Analysis: Some Monte Carlo ResultsJournal of Marketing Research, 1978
- Weak inference with linear models.Psychological Bulletin, 1977
- Additive structure in qualitative data: An alternating least squares method with optimal scaling featuresPsychometrika, 1976
- Preference scales for number and sex of ChildrenPopulation Studies, 1975
- Linear models in decision making.Psychological Bulletin, 1974
- The devil rides again: Correlation as an index of fit.Psychological Bulletin, 1973
- A test of ve-theories of risk and the effect of the central limit theoremActa Psychologica, 1971
- Polynomial psychophysics of riskJournal of Mathematical Psychology, 1970
- The use of nonlinear, noncompensatory models in decision making.Psychological Bulletin, 1970