Data & research question
Thanks to the GPS Player Tracking system of JOHAN Sports, the physical match performance of every player forms an extensive dataset for each match. The system records every movement of a player in three dimensions and translates these movements into variables, such as high intensity sprints (speed 25 km/h or more). The Global Player Index (GPI), developed by Remiqz, objectively measures the added value of each individual player to the overall team performance. This is done by looking at the change in the team’s winning odds during the time that the player was on the pitch.
The main research question is whether it is possible to identify statistically significant physical indicators of player quality in football. The follow up research question is whether there exist significant differences across positions in the impact of these indicators.
Applying econometric models that relate player quality to the physical tracking data result into remarkable results. Most notably, the number of sprints (speed 20 km/h or more) and the average length of sprints are an indicator of player quality. In other words, good players tend to sprint more and for longer distances. Additionally, it was found that the efficiency by which a player moves on the pitch is a significant indicator. In this context, the efficiency is determined by the total activity a player displayed during a match and the distance the player covered in that match. Covering the same distance but with a lower total activity is interpreted as more efficient.
The analysis also incorporates the player’s age, the quality of his teammates and the trend that player quality in the Dutch leagues is diminishing in general. For the age of a player, it appears that the relationship with player quality is nonlinear. In fact, it was found that the average player has its peak in GPI around the age of 27.7 after which the GPI diminishes in general. However, differences can be observed across positions. For instance, wingers appear to peak earlier in their career whereas the peak for fullbacks appears to occur at a later age than 27.7.
Position specific results
Comparing the different positions within the team to each other, it becomes clear that sprinting behaviour is especially important for full backs and centre backs. As there are various types of midfielders each requiring different physical abilities, midfielders are classified into groups with the same characteristics. It was found that for one of these groups, so called box-to-box players, the physical performance is indeed an indicator of player quality. Especially, distance covered at sprint pace was a positive indicator. For strikers the maximum speed turned out to be a positive significant indicator. For wingers, the distance covered at various speeds appeared to be a negative indicator of quality.
There are numerous practical implications of our findings. First, the results confirm that physical indicators of player quality exist. Clubs can use these findings in their recruitment process. In turns out that both sprinting and efficiency are key indicators of player quality. Therefore, clubs can increase player performance by specifically train their players on these aspects. Second, the results show that there exist significant differences across positions in the impact of physical indicators. This shows the need for position specific training schedules. In fact, given the current physical capabilities of every player, the result can be used to develop individual player training schedules in order to improve them on the physical attributes that matter most for him.
Interested in how to apply these findings at your club? Please get in touch with us to discuss the specifics.
(Photos by Pro Shots)