| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 968.46 KB | Adobe PDF |
Orientador(es)
Resumo(s)
The introduction of the Video Assistant Referee (VAR) has been one of the most significant
technological advancements in modern football, aiming to enhance fairness and reduce
human error in refereeing decisions. While its impact on total playing time has been widely
studied, less is known about how VAR affects effective playing time, which refers to the
minutes during which the ball is actively in play. This thesis examines the causal effect of VAR
on effective playing time using Portuguese football as a case study, comparing matches from
the First Division, where VAR was implemented in the 2017/2018 season, to those from the
Second Division, which did not adopt the system.
To estimate the impact of VAR, the study applies a Difference-in-Differences approach,
complemented by an event study design that explores how the effect unfolds over time and
helps assess the validity of key assumptions. A descriptive analysis of match statistics is also
included to provide context for the causal estimates.
The results show that the introduction of VAR is associated with a consistent and statistically
significant decrease in effective playing time. Depending on the model specification, the
reduction ranges from approximately 1.13 to 2.17 percentage points. This impact becomes
more pronounced when accounting for match-specific characteristics such as goals, fouls,
throw-ins, offsides, and corners. Overall, the findings suggest that while VAR enhances
refereeing accuracy, it also contributes to a measurable decline in the time the ball remains in
play. By focusing on a key aspect of match flow, this research offers new insight into how
technological interventions can shape the tempo and experience of the modern game.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
Palavras-chave
VAR Effective Playing Time Impact Evaluation Causal Inference, Difference-in-Differences SDG 3 - Good health and well-being SDG 16 - Peace, justice and strong institutions
