No abstract

Parametric techniques commonly rely on specific distributional assumptions. It is therefore fundamental to preliminarily identify the eventual violations of such assumptions. Therefore, appropriate testing procedures are required for this purpose to deal with a the goodness-of-fit (GoF) problem. This task can be quite challenging, especially with small sample sizes and multivariate data. Previous studiesshowed how a GoF problem can be easily represented through a traditional two-sample system of hypotheses. Following this idea, in this paper, we propose a multi-aspect permutation-based test to deal with the multivariate goodness-of-fit, taking advantage of the nonparametric combination (NPC) methodology. A simulation study is then conducted to evaluate the performance of our proposal and to identify the eventual critical scenarios. Finally, a real data application is considered.

Owing to the development of the technologies of Industry 4.0, recent years have witnessed the emergence of a new concept of supply chain management, namely Supply Chain 4.0 (SC 4.0). Huge investments in information technology have enabled manufacturers to trace the intangible flow of information, but instruments are required to take advantage of the available data sources: big data analytics (BDA) and machine learning (ML) represent important tools for this task. Use of advanced technologies can improve supply chain performances and support reaching strategic goals, but their implementation is challenging in supply chain management. The aim of this study was to understand the main benefits, challenges, and areas of application of BDA and ML in SC 4.0 as well as to understand the BDA and ML techniques most commonly used in the field, with a particular focus on nonparametric techniques. To this end, we carried out a literature review. From our analysis, we identified three main gaps, namely, the need for appropriate analytical tools to manage challenging data configurations; the need for a more reliable link with practice; the need for instruments to select the most suitable BDA or ML techniques. As a solution, we suggest and comment on two viable solutions: nonparametric statistics, and sentiment analysis and clustering.