Match statistics related to winning in the group stage of 2014 Brazil FIFA World Cup

Abstract

Identifying match statistics that strongly contribute to winning in football matches is a very important step towards a more predictive and prescriptive performance analysis. The current study aimed to determine relationships between 24 match statistics and the match outcome (win, loss and draw) in all games and close games of the group stage of FIFA World Cup (2014, Brazil) by employing the generalised linear model. The cumulative logistic regression was run in the model taking the value of each match statistic as independent variable to predict the logarithm of the odds of winning. Relationships were assessed as effects of a two-standard-deviation increase in the value of each variable on the change in the probability of a team winning a match. Non-clinical magnitude-based inferences were employed and were evaluated by using the smallest worthwhile change. Results showed that for all the games, nine match statistics had clearly positive effects on the probability of winning (Shot, Shot on Target, Shot from Counter Attack, Shot from Inside Area, Ball Possession, Short Pass, Average Pass Streak, Aerial Advantage and Tackle), four had clearly negative effects (Shot Blocked, Cross, Dribble and Red Card), other 12 statistics had either trivial or unclear effects. While for the close games, the effects of Aerial Advantage and Yellow Card turned to trivial and clearly negative, respectively. Information from the tactical modelling can provide a more thorough and objective match understanding to coaches and performance analysts for evaluating post-match performances and for scouting upcoming oppositions.

How to be Successful in Football: A Systematic Review

“…Efficiency measures seem to be better predictors for success [21,29,31,44,46]. Liu, Gomez, Lago-Penas and Sampaio [22], Liu, Hopkins and Gomez [53] and Mao, Peng, Liu and Gomez [54] used cumulative logistic-regression in a generalized linear model. They also divided the sample into close matches and unbalanced matches (a cluster analysis based on the goal difference was used) with a cluster analysis and cut-off values.…”

“…For example, Grund [20] introduced network analysis into the research about success factors and Collet [21] revealed new insights into the effect of ball possession using an ordered-logit regression. Liu, Gomez, Lago-Penas and Sampaio [22] used a k-means cluster analysis and a cumulative logistic regression to reveal the factors that differentiate the between winning and losing teams. Overall, the aim of this study is to provide a systematic review of the available literature on performance analysis in elite male football concerning methodologies and results to find out critical factors for success in football and to provide guidance for future research 2 .…”

Match Statistics as Predictors of Team’s Performance in Elite competitive Handball. [Estadística del partido como predictor del rendimiento de equipo en el balonmano de élite].

“…The use of data from the official statistics allow us to contextualize the events in a handball match and to identify the indicators that have a significant influence on the final result. As several authors note (Gómez, Battaglia, Lorenzo, Lorenzo, Jiménez, and Sampaio, 2015;Gómez, Lorenzo, Ibáñez, and Sampaio, 2013;Liu et al, 2015;Sampaio et al, 2013), it is important to take the box score of the match as a global indicator of group performance. The present study is the first to include attack, defense, and goalkeeper variables together as indicators of team performance.…”

“…However, as noted by several authors (Ferrari, Dos Santos, and Vaz, 2014;Gómez, Lago-Peñas, Viaño, and González-Garcia, 2014;Teles and Volossovith, 2015;Vaz, van Rooyen, and Sampaio, 2010), team performance indicators should consider not only the final result but also the number of points scored. Indeed, recent studies have analysed match statistics in several sports settings (Georgiana and Aurelia, 2014;Liu, Gómez, Lago-Peñas, and Sampaio, 2015;Lupo, Condello, Capranica, and Tessitore, 2014;Sampaio, Ibáñez, and Lorenzo, 2013). Volossovitch (2013) the lack of studies considering the dynamics of the game versus the studies addressed from a static perspective, where the time in which the game actions occur is not taken into account.…”

Football scout analysis models (based in the 2013/2014 Champions League)

“…Passes certos apresentou relação positiva com fi nalizações a gol e posse de bola; e uma relação negativa com fi nalizações totais, faltas cometidas e passes errados. Times com maior número de vitórias apresentaram maior número de passes certos, fi nalizações a gol e posse de bola quando comparado com times que menos venceram 11,19,21 .…”