Multivariate Exploratory Comparative Analysis of LaLiga Teams: Principal Component Analysis.

Area of Science:

• Sports Science
• Data Analysis in Football

Background:

• Traditional analysis often presents individual performance metrics.
• Reducing complex datasets is crucial for better interpretation of team characteristics.

Purpose of the Study:

• To apply Principal Component Analysis (PCA) for simplifying extensive football performance data.
• To conduct a comparative analysis between top and bottom-ranked teams in LaLiga using PCA-derived components and multiple linear regression.

Main Methods:

• Utilized PCA to reduce a large data matrix of football match statistics.
• Employed multiple linear regression for comparative analysis between elite and struggling teams.
• Analyzed data from LaLiga seasons 2015/16, 2016/17, and 2017/18.

Main Results:

• Superior teams demonstrated more successful passes and dynamic offensive transitions.
• Lower-performing teams exhibited more defensive actions, fewer goals, and prolonged ball possession in the final third.
• Key discriminating factors identified: goals, final third possession, effective shots, and crosses.

Conclusions:

• PCA effectively differentiates team performance characteristics.
• Identified specific Key Performance Indicators (KPIs) that distinguish successful football teams.
• Findings enhance understanding of critical performance metrics in professional football.