A0340
Title: A multivariate permutation test for the analysis of market research data
Authors: Riccardo Ceccato - University of Padova (Italy)
Rosa Arboretti - University of Padova (Italy)
Elena Barzizza - Università degli studi di Padova (Italy)
Nicolo Biasetton - Università degli Studi di Padova (Italy)
Marta Disegna - University of Padova (Italy) [presenting]
Luca Pegoraro - University of Padova (Italy)
Luigi Salmaso - University of Padova (Italy)
Abstract: The Nonparametric Combination (NPC) is a flexible methodology that can be adopted to deal with a wide range of complex scenarios. It allows us to propose quite powerful testing procedures to undertake problems involving the comparison of two populations when a multivariate outcome is observed. We propose a new NPC-based test to deal with a particular multivariate scenario in which two paired samples and multiple data types are available. This technique is then adopted for the analysis of market research data. A questionnaire was indeed submitted to multiple respondents, asking them to evaluate a product in terms of a certain set of KPIs (i.e. ordinal variables were gathered) after two different time frames. A number of experiments were also conducted and additional KPIs were measured (i.e. numeric variables were collected) after the same two-time frames. The NPC-based test was therefore adopted to compare the performances of the product across time.
