Στατιστικά μοντέλα για την ανάλυση της απόδοσης στο ευρωπαϊκό μπάσκετ συλλόγων κατά την τελευταία δεκαετία

Καραβασίλης, Δημήτρης

Statistical models for the analysis of performance in European club basketball over the last decade

Master Thesis

Author

Καραβασίλης, Δημήτρης

Date

2026-03

Abstract

In the modern age, data constitute one of the most important resources for understanding complex systems and processes. Their systematic collection and analysis make it possible to extract useful information and to support evidence-based decision making across a wide range of applications, from the economy and industry to sports. In the field of basketball, the use of statistical data has transformed the way teams design their game strategies, evaluate their performance, and prepare against their opponents. Data analysis now offers an advanced level of understanding of the game, enhancing the competitiveness of clubs in top-level competitions. The present thesis examines the performance of EuroLeague teams over the last fifteen years. In addition to classical statistical variables, advanced indicators are also employed, such as game pace (Pace), offensive rebounding percentage (OR%), and shooting efficiency metrics eFG% and TS%, with the aim of gaining a deeper understanding of the factors that influence success. A descriptive analysis of the data is first presented through tables and graphical representations for both the regular seasons and the Playoffs. Subsequently, normality and correlation tests are conducted, and generalized linear models are applied in order to identify the most important variables that affect qualification to the Playoffs, finishing in the top four of the regular-season standings (Top-4), as well as the probability of home-court advantage upsets in the Playoff series. Furthermore, machine learning techniques are employed to develop classification and clustering models, in order to investigate the extent to which the qualification of teams to the Playoffs can be predicted. Finally, the main conclusions of the thesis are presented.

Postgraduate Studies Programme

Εφαρμοσμένη Στατιστική

Department

Σχολή Χρηματοοικονομικής και Στατιστικής. Τμήμα Στατιστικής και Ασφαλιστικής Επιστήμης

Number of pages

147

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/18988

Collections

Τμήμα Στατιστικής και Ασφαλιστικής Επιστήμης

Show full item record

Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα