The rating problem arises very often in statistical surveys, where respondents are asked to evaluate several topics of interest (products, services, treatments, etc.). In this framework, a new approach is represented by a class of mixture models (Covariates in the mixture of Uniform and shifted Binomial distributions, CUB models), proposed by Piccolo (2003), D’Elia and Piccolo (2005) and Piccolo (2006). Together with parametric inference, a permutation solution to test for covariates effects, when a univariate response is considered, has been discussed in Bonnini et al. (2011), where the method has been proved to be well performing and competitive with respect to the asymptotic solution. In the present work we perform an extension of the simulation study to prove the good power behavior of the permutation solution also in other different situations. The method is also applied to real data regarding the analysis of the main reasons that drive tourists to choose Sesto/Alta Pusteria’s Dolomites (an area of the Trentino Alto Adige region in Italy) as resort for their holidays.
Advances in CUB models with application to the evaluation of natural parks in the dolomites
ARBORETTI GIANCRISTOFARO, ROSA;
2011
Abstract
The rating problem arises very often in statistical surveys, where respondents are asked to evaluate several topics of interest (products, services, treatments, etc.). In this framework, a new approach is represented by a class of mixture models (Covariates in the mixture of Uniform and shifted Binomial distributions, CUB models), proposed by Piccolo (2003), D’Elia and Piccolo (2005) and Piccolo (2006). Together with parametric inference, a permutation solution to test for covariates effects, when a univariate response is considered, has been discussed in Bonnini et al. (2011), where the method has been proved to be well performing and competitive with respect to the asymptotic solution. In the present work we perform an extension of the simulation study to prove the good power behavior of the permutation solution also in other different situations. The method is also applied to real data regarding the analysis of the main reasons that drive tourists to choose Sesto/Alta Pusteria’s Dolomites (an area of the Trentino Alto Adige region in Italy) as resort for their holidays.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.