Sensitivity Analysis and Robust Approach in Multidimensional Scaling: An Evaluation of Customer Satisfaction

Abstract

Multidimensional scaling (MDS) methods are devoted par excellence to representing a set of objects in a low-dimensional Euclidean space by preserving, as far as possible, the proximities between the objects themselves. Like other data analysis techniques, MDS methods treat a set of data as the entire population of interest. It is therefore important to determine the stability and robustness of the results against possible perturbations or errors present in the data. This issue is particularly important in customer satisfaction analysis, where satisfaction indicators and customer ranking can be heavily influenced by such anomalies. These kinds of problems are specifically addressed in this work. Starting from commonly applied methods, a combination of sensitivity and robust analysis will be proposed. A case study will then be considered.

Key Words:

• Classical multidimensional scaling
• forward search
• Gower’s general coefficient of similarity
• jackknife
• mixed data

Additional information

Notes on contributors

Nadia Solaro

Nadia Solaro is an Assistant Professor of Statistics at the Department of Statistics, University of Milan-Bicocca. She holds a degree in Political Sciences and Ph.D. in Statistics from University of Milan. Her main research interests include multilevel models, data analysis techniques, statistical methods in clinical research and quality evaluation in health care system. Since 2004 she has been collaborating for scientific research with the Centre of Neurovegetative Therapy, “Luigi Sacco” Hospital, Milan.