Abstract
We present a new statistical approach to measure customer satisfaction aimed at understanding theoretical and empirical evidence about the causal relationships among motivations, personal characteristics and expressed agreement. The approach is based on a mixture model that is able to express the stated evaluation via the subjects’ covariates. Specifically, it examines and compares the uncertainty of the answer and the feeling towards the items. After a brief review of current approaches to statistical methods for ordinal data, we provide a discussion of our proposal for modelling the responses of customers. Two case studies illustrate the benefit of model and some general considerations conclude the paper.
Additional information
Notes on contributors
Maria Iannario
Maria Iannario is Researcher in Statistics, Department of Statistical Sciences, University of Naples Federico II. She received Laurea in Political Sciences (2001) and in Statistics (2007), and received Ph.D. degree (2005) for a study in applied methods for environmental planning. During 2005 she has been Lecturer in Applied Statistics at University of Naples Federico II. Her current works focus on evaluation methods and statistical models for ordinal data, and she published many scientific papers on these research topics.
Domenico Piccolo
Domenico Piccolo is Professor of Statistics, Department of Statistical Sciences, University of Naples Federico II. He received Laurea in Statistical Sciences (1970) at University of Rome La Sapienza. He is a member of ASA and SIS, and Associate Editor of Statistica and Quaderni di Statistica journals. He promoted research projects, national and international conferences, courses and seminars, and chaired national projects leading Italian institutions to a unifying approach to seasonal adjustment, according to the directives of the European Community. He has made significant researches and teaching in Italy and abroad mainly focused on statistical methods, inference theory, time series analysis and ordinal variable modelling. He is the author of more than 100 scientific works and standard textbooks in Statistics and Time Series Analysis. He is currently involved in researches and projects related to the monitoring and evaluation aspects using statistical methods, by introducing a novel approach and a new class of models.