Following the debate between the proponents of the ranking and rating methods for the measurement of values, this article considers the hypothesis that a person’s responses in ranking and rating tasks are governed by the same unidimensional latent trait. The hypothesis was tested through a probabilistic modeling approach. The results of a joint application of the rating scale and ranking models indicated that this latent common trait exists and seems to have a role in molding the relationship between the latent variable and the observable responses in both ranking and rating formats.
Rating, ranking or both? A joint application of two probabilistic models for the measurement of values
DE CHIUSOLE, DEBORA;STEFANUTTI, LUCA
2011
Abstract
Following the debate between the proponents of the ranking and rating methods for the measurement of values, this article considers the hypothesis that a person’s responses in ranking and rating tasks are governed by the same unidimensional latent trait. The hypothesis was tested through a probabilistic modeling approach. The results of a joint application of the rating scale and ranking models indicated that this latent common trait exists and seems to have a role in molding the relationship between the latent variable and the observable responses in both ranking and rating formats.File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.