Bayesian analysis of Formula One race results: disentangling driver skill and constructor advantage.

Area of Science:

• Sports Analytics
• Statistical Modeling
• Motorsport Science

Background:

• Formula One performance relies on driver skill and constructor advantage, making it challenging to isolate individual contributions.
• Key questions include identifying the best drivers and constructors and quantifying their impact on race success.

Purpose of the Study:

• To quantitatively assess driver skill and constructor advantage in Formula One during the hybrid era (2014-2021).
• To develop and apply a novel statistical method for analyzing race performance data.

Main Methods:

• A Bayesian multilevel rank-ordered logit regression model was developed to analyze individual race finishing positions.
• The model was applied to data from the 2014-2021 Formula One hybrid era seasons.

Main Results:

• The model accurately describes race result data, enabling precise inferences on driver and constructor performance.
• Lewis Hamilton and Max Verstappen are identified as the top drivers.
• Mercedes, Ferrari, and Red Bull are the leading constructors.
• Constructor advantage accounts for approximately 88% of the variance in race results.

Conclusions:

• The study provides a robust method for ranking drivers and constructors in Formula One.
• Constructor performance is the dominant factor influencing race outcomes.
• The methodology can be extended to analyze performance in other competitive sports.