[Forum SIS] Avviso di seminario

[Francesca De Battisti (francesca.debattisti)]

Martedì 24 gennaio 2012 


Emanuela Raffinetti (Università degli Studi di Milano) terrà il seminario dal titolo:


 


“New Statistical Perspectives in Customer Satisfaction Survey”


 


presso l'Aula Seminari del Dipartimento di Scienze Economiche, Aziendali e Statistiche della Facoltà di Scienze Politiche dell'Università degli Studi di Milano (via Conservatorio, 7). 


 


Il seminario è programmato alle ore 12.15. 


 


ABSTRACT


Most people in business know they need feedback from customers in order to make service more in line with customer needs and expectations. In fact, by exploiting the clear and strong relationship between the quality of a service or a product and customer satisfaction, one can achieve business success. However, too often, the process of measuring customer satisfaction and perception is more complex and convoluted than it needs to be since ordinal data are involved.


The present contribution proposes a novel methodological approach which is the result of two recent procedures developed in order to improve the analysis of categorical and ordinal data. The proposal consists in extending the Lorenz curve tool to ordinal data and in defining a novel Gini measure, called “ranks-based Gini measure”. Through the ranks-based Gini measure, one can obtain information about the customers’ agreement or disagreement concerning the quality evaluation of a service or a product. 


A further open issue, when dealing with ordinal data, is the analysis of dependence relations between an ordinal variable and a set of generic variables. The idea is resorting to the the so called Lorenz zonoid which corresponds to the Gini measure in the univariate case. More precisely, we consider the Lorenz zonoid of a multiple linear regression function characterized by k explanatory variables and we define the partial contribution due to the progressive introduction of each covariate into the model. This leads to the definition of a new partial dependence measure called “Relative Gini Index” which provides a novel stopping rule for the forward selection procedure when the involved relevant variables exhibit different nature.


The result consists in a new multiple linear regression model characterized by an ordinal response variable, which denotes the quality assessment depicted by the customer responses given to the questionnaire, and a set of explanatory variables which represent the single evaluated topics. The model so obtained will be called “Ranks-Zonoids linear regression model”, since it combines the application of ranks and Lorenz zonoids.







Tutti gli interessati sono invitati a partecipare.

 
***********************************************************
Francesca De Battisti
Dipartimento di Scienze Economiche, Aziendali e Statistiche 
Sezione Statistica e Matematica
(III piano, studio n. 29)
Via Conservatorio 7
20122 - Milano
Tel: 02.50321464
Fax: 02.50321505
***********************************************************
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20120110/662766fc/attachment.html>