CUB models are useful for studying ordinal data in rating surveys. The response probabilities are modelled as a convex combination of a shifted Binomial and a discrete Uniform distribution, to capture respondent psychological behaviour of being only partially able to quantify his/her feeling toward a specific item. A recent extension of CUB models, called the VCUB model, replaces the Uniform component with a variety of distributions, allowing for a more flexible description of respondent uncertainty. The comparison of different options can be interesting also from a psychological point of view. This work studies the necessity of multiple comparison adjustments, whenever several specifications seem adequate.
Some considerations on VCUB models / Anna Gottard. - ELETTRONICO. - (2013), pp. 241-244. (Intervento presentato al convegno 9th Meeting of the Classification and Data Analysis Group tenutosi a Modena nel 18-20 Settembre 2013).
Some considerations on VCUB models
GOTTARD, ANNA
2013
Abstract
CUB models are useful for studying ordinal data in rating surveys. The response probabilities are modelled as a convex combination of a shifted Binomial and a discrete Uniform distribution, to capture respondent psychological behaviour of being only partially able to quantify his/her feeling toward a specific item. A recent extension of CUB models, called the VCUB model, replaces the Uniform component with a variety of distributions, allowing for a more flexible description of respondent uncertainty. The comparison of different options can be interesting also from a psychological point of view. This work studies the necessity of multiple comparison adjustments, whenever several specifications seem adequate.File | Dimensione | Formato | |
---|---|---|---|
Pages from CLADAG2013_Abstract.pdf
Accesso chiuso
Tipologia:
Altro
Licenza:
Tutti i diritti riservati
Dimensione
103.73 kB
Formato
Adobe PDF
|
103.73 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.