Game interruptions in elite soccer

Elite Soccer Players Do Not Cover Less Distance in the Second Half of the Matches When Game Interruptions Are Considered

ABSTRACT

Rey, E, Kalén, A, Lorenzo-Martínez, M, López-Del Campo, R, Nevado-Garrosa, F, and Lago-Peñas, C. Elite soccer players do not cover less distance in the second half of the matches when game interruptions are considered. J Strength Cond Res 38(4): 709-713, 2024-This study aimed to analyze quantitative differences in the physical demands of male elite soccer players between the first and second halves during official matches, accounting for effective playing time (the duration of play after subtracting the game interruptions) and playing positions. A total of 4,249 individual match observations of 412 outfield players competing in the Spanish first division league (LaLiga) were undertaken during the 2018-2019 season, using a computerized tracking system (TRACAB, Chyronhego, New York, NY). The players were classified into 5 positional roles: central defenders (CD), external defenders (ED), central midfielders (CM), external midfielders (EM), and forwards (F). The main results showed that in contrast to those observed when total playing time was considered, independent of playing position, there were no significant differences on high-speed running (HSR) (5.5 ± 2.4 vs. 5.5 ± 2.4 m·min -1 ) and sprint (5.3 ± 3.3 vs. 5.4 ± 3.3 m·min -1 ) distances between the first and second halves in professional soccer players when the effective playing time was considered. However, differences in match running performance at HSR and sprint distances between the first and second halves were dependent on players' playing position. Whereas ED and EM maintained HSR and sprint efforts during the second half, CD and CM significantly increased ( p < 0.001) the distance covered at sprint during the second period of the match. Contrarily, F were unable to maintain their HSR (6.2 ± 2.3 vs. 5.9 ± 3.3 m·min -1 ) and sprint (7.0 ± 3.5 vs. 6.5 ± 3.4 m·min -1 ) match running performances during the second half. Such findings demonstrate that total playing time could overestimate fatigue-induced performance declines. Thus, effective playing time and playing position should be taken into account when interpreting the match running performance of professional soccer players.

Using Microtechnology and the Fourier Transform for the Analysis of Effective Activity Time in Professional Soccer

ABSTRACT

Oliva-Lozano, JM, Chmura, P, Granero-Gil, P, and Muyor, JM. Using microtechnology and the Fourier Transform for the analysis of effective activity time in professional soccer. J Strength Cond Res 37(12): 2491-2495, 2023-This study aimed to investigate the use of the fast Fourier transform (FFT) for the analysis of effective activity time in professional soccer by (a) exploring the relationship between this variable and standard external load parameters and (b) analyzing the effective activity time during official professional soccer matches. Twenty-six male players participated in the study. Each player was categorized as midfielder, central defender, full-back, wide-midfielder, or forward. Tracking systems based on inertial sensors (4 3D accelerometers, 3 3D gyroscopes, and 1 magnetometer), and global positioning systems technology were used to collect external load measures for 35 matches. Each match was analyzed considering 15-minute periods to explore the evolution of effective activity time during the matches. The extra time from each match was also included. Fast Fourier transform duration may be a representative variable of effective activity time, given the strong positive correlation with the external load variables ( p < 0.001). The linear regression analysis showed that the variables that significantly contributed to the model ( R2 = 0.97) were the total of steps and the distance covered. The mean effective activity time in soccer match play was ∼48.69 minutes. This time significantly changed depending on factors such as the period of the match ( F = 239.05; p < 0.001; ηp 2 = 0.60) or playing position ( F = 16.99; p < 0.001; ηp 2 = 0.06). The greatest effective activity time was observed for all playing positions in the 0'-15' period. However, the 60'-75' period showed the lowest effective activity times compared with the rest of the 15-minute periods for all positions except for forwards (75'-90'). From a practical standpoint, sports performance practitioners may consider these results to improve the individualization of training and match demands. Also, a more accurate indicator of exercise intensity may be obtained (e.g., multiplying the rating of perceived exertion by the effective activity time).

Effects of tactical dimension and situational variables in throw-ins on the offensive performance in football

The aim of the study was to describe the usual practices in the execution of throw-ins by La Liga teams during the 2021-2022 season, identify tactical indicators related to the outcome of plays that start with a throw-in, calculate their predictive power, and finally analyse the influence of situational variables on the effectiveness of these plays. A total of 2,658 throw-ins, during 80 matches were analysed. Two UEFA PRO coaches designed an ad hoc observation instrument "Thrinfoot" and two observers coded the data after a training process. Inter and intra-observer reliability was calculated using Cohen´s Kappa coefficient, revealing almost perfect agreement. Multinomial logistic regression was applied to predict the throw-ins outcome (p<0.05). Results showed how fast throw-ins (OR = 0.7, p<0.05), without pressing (OR = 0.4, p<0.001), short and backwards (OR = 0.3, p<0.01) in the central zone (OR = 0.6, p<0.01) and made in the 16´-30´ (OR = 0.6, p<0.01), 61´-75´ (OR = 0.7, p< 0.05) periods, presented higher probabilities of continuing with possession. Match status losing>2 (OR = 4.1, p< 0.05) showed higher probabilities of success. On the other hand, throw-ins from the defensive zone presented higher probabilities of unsuccess (OR = 8.6, p<0.01) and losing possession (OR = 1.8, p<0.01). Finally, the bottom teams showed the highest probability of losing the ball. In conclusion, tactical indicators such as duration, press, distance, direction and zone were identified as key performance indicators and the situational variables team quality, match status and time influence the outcome of throw-ins. These findings provide valuable insights to coaches regarding the factors that influence the outcome of throw-ins. This allows them to design optimal strategies for both executing and defending these plays based on the game situation and their immediate aims.

The influence of ball in/out of play and possession in elite soccer: Towards a more valid measure of physical intensity during competitive match-play

The physical demands of soccer match-play have typically been assessed using a low-resolution whole match approach ignoring whether the ball is in or out of play (BIP/BOP) and during these periods which team has possession. This study investigated the effect of fundamental match structure variables (BIP/BOP, in/out of possession) on the physical demands, and especially intensity, of elite match-play. For 1083 matches from a major European league, whole match duration, and player physical tracking data, were divided into BIP/BOP, and in/out of possession periods throughout the match, using on-ball event data. These distinct phases were used to derive absolute (m) and rate (m·min-1) of distance covered in total and within six speed categories during BIP/BOP and in/out possession. The rate of distance covered, an index of physical intensity, was >2-fold greater during BIP vs BOP. Whole match total distance covered was confounded by BIP time and poorly associated with physical intensity during BIP (r = 0.36). Whole match rates of distance covered substantially underestimated those during BIP, particularly for higher running speeds (∼-62%). Ball possession markedly effected physical intensity, with the rates of distance covered running (+31%), at high-speed (+30%) and in total (+7%) greater out than in possession. Whole match physical metrics underestimated the physical intensity during BIP, and thus the rate(s) of distance covered during BIP are recommended for accurate measurement of physical intensity in elite soccer. The greater demands of being out of possession support a possession-based tactical approach to minimise fatigue and its negative consequences.

Effective playing time affects technical-tactical and physical parameters in football

Effective playing time has been debated as a topic of major concern in football. Thus, the current experimental study aimed to investigate the effects of effective playing time on technical-tactical and physical match parameters in football. One hundred and seventy-nine male highly trained football players (aged 27.9 ± 5.1 years) from twelve teams performed two different match-play conditions: 45 min of match-play without stopping the chronometer (T45), and 30 min of match-play by stopping the chronometer every time the ball was out-of-play (T30). T30 presented a significantly higher total time (49:30 vs. 45:00 min; p = <.001; ES = 0.76), effective playing time (28:70 vs. 26:80 min; p = <.001; ES = 0.62), and stopped time (20:60 vs. 18:20 min; p = 0.003; ES = 0.38) compared to T45. Total ball possession (54.4% vs. 45.6%; p = 0.002) and 1/3 ball possession (55.3% vs. 44.7%; p = 0.018) was higher in T30 condition when compared to T45. Regarding match external load, total distance covered (4,899 vs. 4,481 m; p = <.001; ES = 0.71), moderate-speed running (607 vs. 557 m; p = 0.002; ES = 0.26) and high-speed running (202 vs. 170 m; p = <.001; ES = 0.33), high-speed activities (284 vs. 245 m; p = 0.003; ES = 0.24), accelerations (27 vs. 24; p = <.001; ES = 0.32), and decelerations (31 vs. 28; p = 0.005; ES = 0.26) were higher in T30 compared to T45. In conclusion, these findings suggest that higher effective playing time may affect technical-tactical and physical parameters during football games.

Accumulated Workload Differences in Collegiate Women's Soccer: Starters versus Substitutes

The purpose of this study was to estimate the workloads accumulated by collegiate female soccer players during a competitive season and to compare the workloads of starters and substitutes. Data from 19 college soccer players (height: 1.58 ± 0.06 m; body mass: 61.57 ± 6.88 kg) were extracted from global positioning system (GPS)/heart rate (HR) monitoring sensors to quantify workload throughout the 2019 competitive season. Total distance, distance covered in four speed zones, accelerations, and time spent in five HR zones were examined as accumulated values for training sessions, matches, and the entire season. Repeated-measures ANOVA and Student's t tests were used to determine the level of differences between starter and substitute workloads. Seasonal accumulated total distance (p < 0.001), sprints (≥19.00 km/h; p < 0.001), and high-speed distance (≥15.00 km/h; p = 0.005) were significantly greater for starters than substitutes. Accumulated training load (p = 0.08) and training load per minute played in matches (p = 0.08) did not differ between starters and substitutes. Substitutes had similar accumulated workload profiles during training sessions but differed in matches from starters. Coaches and practitioners should pursue strategies to monitor the differences in workload between starters and substitutes.

Validity and reliability of the physiological and perceptual responses elicited during a novel treadmill-based Soccer Referee Simulation (SRS)

Purpose

This study explored the validity and reliability of the physiological and perceptual responses elicited during a novel treadmill-based Soccer Referee Simulation (SRS).

Methods

Following the collection of baseline measures and habituation procedures, eight sub-elite soccer referees completed a single trial of the SRS whereby measures of heart rate (HR), oxygen uptake (V̇O2), blood lactate concentrations ([La−]b), and differential ratings of perceived exertion (RPE) were obtained. Referees’ HR responses were also monitored during a series of competitive matches (5 match observations per referee). For the reliability aspect of the investigation, eight well-trained males with soccer playing experience and a comparable physiological profile were initially habituated, and thereafter completed three separate trials of the SRS during which the reliability of the selected outcome variables were ascertained. Trials were separated by 3–7 days and performed under standardised conditions.

Results

No differences were evidenced between the SRS and match play in relation to measures of mean HR (P = 0.444; ES = 0.29), peak HR (P = 0.074; ES = 0.74), or HR-based training impulse (P = 0.498; ES = 0.25). Additionally, no systematic differences were detected between reliability trials for any of the measured outcome variables (P ≥ 0.293), whilst good levels of reliability were observed for measures of mean HR (ICC = 0.94; CV = 3.1%), peak HR (ICC = 0.93; CV = 2.2%), HR-based training impulse (ICC = 0.95; CV = 10.0%), mean V̇O2 (ICC = 0.95; CV = 2.6%); [La−]b (ICC ≥ 0.89; CV ≤ 11.5%), and differential RPE (ICC ≥ 0.94; CV ≤ 15.1%).

Conclusion

The SRS represents a valid and reliable protocol that closely replicates the physiological and decision-making demands of soccer refereeing.

Predicting the in-game status in soccer with machine learning using spatiotemporal player tracking data

An important structuring feature of a soccer match is the in-game status, whether a match is interrupted or in play. This is necessary to calculate performance indicators relative to the effective playing time or to find standard situations, ball actions, and other tactical structures in spatiotemporal data. Our study explores the extent to which the in-game status can be determined using time-continuous player positions. Therefore, to determine the in-game status we tested four established machine learning methods: logistic regression, decision trees, random forests, and AdaBoost. The models were trained and evaluated using spatiotemporal data and manually annotated in-game status of 102 matches in the German Bundesliga. Results show up to 92% accuracy in predicting the in-game status in previously unknown matches on frame level. The best performing method, AdaBoost, shows 81% precision for detecting stoppages (longer than 2 s). The absolute time shift error at the start was ≤ 2 s for 77% and 81% at the end for all correctly predicted stoppages. The mean error of the in-game total distance covered per player per match using the AdaBoost in-game status prediction was − 102 ± 273 m, which is 1.3% of the mean value of this performance indicator (7939 m). Conclusively, the prediction quality of our model is high enough to provide merit for performance diagnostics when teams have access to player positions (e.g., from GPS/LPM systems) but no human-annotated in-game status and/or ball position data, such as in amateur or youth soccer.

Factors That Influence Actual Playing Time: Evidence From the Chinese Super League and English Premier League

This study explored factors that influence actual playing time by comparing the Chinese Super League (CSL) and English Premier League (EPL). Eighteen factors were classified into anthropogenic and non-anthropogenic factors. Fifty CSL matches (season 2019) and 50 EPL matches (season 2019–2020) were analyzed. An independent sample t-test with effect size (Cohen’s d) at a 95% confidence interval was used to evaluate differences in the influencing factors between the CSL and EPL. Two multiple linear regression models regarding the CSL and EPL were conducted to compare the influencing factors’ impact on actual playing time. The results showed that the average actual playing time (p &lt; 0.05, 0.6 &lt; ES = 0.610 &lt; 1.2) and average game density (p &lt; 0.05, 0.2 &lt; ES = 0.513 &lt; 0.6) in the EPL were significantly higher than in the CSL. The average time per game for general fouls (p &lt; 0.05, 1.2 &lt; ES = 1.245 &lt; 2.0) and minor injuries (p &lt; 0.05, 0.2 &lt; ES = 0.272 &lt; 0.6) in the CSL was significantly higher than in the EPL. The average time allocated to off-field interferences in the CSL was significantly higher than in the EPL, while the average time allocated to throw-ins (out-of-bounds) in the CSL was significantly lower than in the EPL (p &lt; 0.05, 0.2 &lt; ES = 0.556 &lt; 0.6). The study showed that actual playing time in CSL games was more affected by anthropogenic factors than in the case of EPL games, while both leagues were equally affected by non-anthropogenic factors. This study provides a reference for coaches to design effective training and formulate game strategies for elite soccer leagues.

Football Match Dynamics Explored by Recurrence Analysis

A widely accepted notion of football matches in performance analysis (PA) is to consider them as dynamic interaction processes with emerging behaviors. The description and analysis of these processes requires specific methods. Recurrence analysis is a technique for analyzing complex systems in many domains like astrophysics, earth sciences, engineering, biology, cardiology, and neuroscience. Its general concept is to examine the recurrence behavior of a system, as in when, how often and how close its trajectory in a phase space returns to a previous state. The aim of the study is to apply recurrence analysis to football matches. Positional data from 21 football matches of a German Bundesliga team were examined. The phase space was made up of the field players' x,y-positions at each second of the match. For each pair of seconds, the average distance of all the players between their positions at these two time points was calculated. Recurrence plots (RPs) were obtained by color-coding these distances. With a recurrence threshold of rt = 9 m and a minimum line length of lmin = 3 s, general recurrence parameters were calculated to characterize the individual recurrence behaviors of each match. Three football-specific recurrence parameters were defined to represent recurrence properties of open play. RPs showed commonalities (typical features indicating set plays and continuous gameplay) as well as unique structures during each match (number, distribution, and sequence of typical features). The recurrence parameters showed several significant correlations with traditional performance indicators like number of goals and passes completed, e.g., the correlation between number of goals and recurrence rate is r = -0.622 (p = 0.003). By extending the sample and design of recurrence studies, there is great potential for recurrence analysis to improve both the practical and theoretical potential of performance analysis.

Prediction of Match Outcomes with Multivariate Statistical Methods for the Group Stage in the UEFA Champions League

The aim of this study was to analyse the win, draw, and loss outcomes of soccer matches with situational variables and performance indicators. Data from group stage matches spanning the ten years between the 2010/2011 and 2019/2020 seasons in the European Champions League, were used. One-way analysis of variance (ANOVA) and Tukey HSD (honestly significant difference) tests indicated performance indicators which affected the outcome of matches. K-mean clustering, with statistically significant variables, categorized the quality of the opposition into three clusters: weak, balanced, and strong. Multidimensional scaling (MDS) and decision tree analysis were applied to each of these clusters, highlighting that performance indicators of the teams differed according to the quality of their opponent. Furthermore, according to the decision tree analysis, certain performance indicators, including scoring first and shots on target, increased the chances of winning regardless of the quality of the opposition. Finally, particular performance indicators increased the chance of winning, while others decreased this, in accordance with the quality of the opposition. These findings can help coaches develop different strategies, before or during the match, based on the quality of opponents, situational variables, and performance indicators.

Effect of formation, ball in play and ball possession on peak demands in elite soccer

This study examined the most demanding passages of match play (MDP) and the effects of playing formation, ball-in-play (BiP) time and ball possession on the 1-min peak (1-minpeak) demand in elite soccer. During 18 official matches, 305 individual samples from 223 Italian Serie A soccer players were collected. MDP and 1-minpeak were calculated across playing position (central defenders, wide defenders, central midfielders, wide midfielders, wide forwards and forwards). Maximum relative (m·min-1) total distance (TD), high-speed running (HSR), very high-speed running (VHSR), sprint (SPR), acceleration/deceleration (Acc/Dec), estimated metabolic power (Pmet) and high-metabolic load (HML) distance were calculated across different durations (1-5, 10, 90 min) using a rolling method. Additionally, 1-minpeak demand was compared across playing formation (3-4-1-2, 3-4-2-1, 3-5-2, 4-3-3, 4-4-2), BiP and ball/no-ball possession cycles. MDP showed large to verylarge [effect-size (ES): 1.20/4.06] differences between 1-minpeak vs all durations for each parameter. In 1-minpeak, central midfielders and wide midfielders achieved greater TD and HSR (ES:0.43/1.13) while wide midfielders and wide forwards showed greater SPR and Acc/Dec (ES:0.30/1.15) than other positions. For VHSR, SPR and Acc/Dec 1-minpeak showed fourfold higher locomotor requirements than 90-min. 1-minpeak for Acc/Dec was highest in 4-3-3 for forwards, central and wide midfielders. 1-minPeak was lower during peak BiP (BiPpeak) for HSR, VHSR and Acc/Dec (ES: -2.57/-1.42). Comparing with vs without ball possession, BiPpeak was greater (ES: 0.06/1.48) in forwards and wide forwards and lower (ES: -2.12/-0.07) in central defenders and wide defenders. Positional differences in MDP, 1-minpeak and BiPpeak were observed. Soccer-specific drills should account for positional differences when conditioning players for the peak demands. This may help practitioners to bridge the training/match gap.

Video assistant referees (VAR): The impact of technology on decision making in association football referees

The use of technology has been proposed to improve decision-making in sport officials. The implementation of the video Assistant Referee (VAR) in association football is one example of how technology can be used to assist decision making, although its impact remains unknown. In 2195 competitive football matches across 13 countries, the VAR conducted 9732 checks for potential match-changing incidents, with the median duration of a check being 22 seconds. The checks resulted in a total of 795 reviews, with a median duration of 62.0 s for on-field reviews (N = 534) and 15.0 s for VAR-only reviews (N = 261).We report that the predictive odds for making the correct decision after VAR intervention were significantly higher than for the initial referee's decision, with accuracy increasing from 92.1% to 98.3%. Findings have implications for the current debate about the introduction of technology in association football and may help set guidelines regarding the use of technology across other sports and professional domains.

Show cards of the Global Physical Activity Questionnaire (GPAQ) - do they impact validity? A crossover study

Background

The Global Physical Activity Questionnaire (GPAQ) is applied internationally as a tool to assess the level of physical activity. The GPAQ was designed as an interview, including the use of show cards, which visualise activities of moderate and intensive physical activity and support the distinction between these intensities. The self-administered version of the GPAQ is used in the application-oriented research for reasons of economy and practicality. However, the use of show cards often remains unknown.

The aim of the present study was to examine differences in validity between two self-administered versions of the GPAQ with and without show cards.

Methods

In this crossover study, two groups (n = 54; 57.4% female; 28.3 ± 12.2 years) received the GPAQ with or without show cards after 7 days and the respective other version after additional 7 days. For validation, all participants wore an accelerometer (ActiGraph GT3X+) on all 14 days.

Differences between GPAQ versions and accelerometer data were compared by Wilcoxon signed rank test. Additionally, Spearman analyses and Bland-Altman plots were calculated.

Results

No statistically significant difference between the GPAQ versions could be found in regard to the accuracy of physical activity assessment (p > 0.05).

Both GPAQ versions show similar correlation coefficients for vigorous physical activity (rho = 0.31–0.42) and sedentary behaviour (rho = 0.29–0.32). No statistically significant correlation was found for physical activity of moderate intensity. The Bland-Altman plots support these results, as both GPAQ versions have the same trends in terms of overestimation and underestimation of physical activity.

Conclusion

The use of show cards had no significant impact on questionnaire validity. Therefore, both GPAQ versions can be applied interchangeably. Nevertheless the exact description of application of the GPAQ is desirable in terms of reproducibility and transparent scientific research.

Observational Studies in Male Elite Football: A Systematic Mixed Study Review

Objective: This systematic mixed study review, focuses on the use of observation methodology in elite men's football matches, which constitutes an innovative approach, that opens up a new panorama of useful and productive research.

Method: The methods used in this study follow the recommendations for systematic reviews and meta-analysis guidelines (PRISMA). The search was carried out in five databases. Ninety-four articles out of 3,195 were selected and analyzed. In order to achieve a quality assessment, the guide was used to inform evaluations based on observation methodology (GREOM) (Portell et al., 2015), recognized by the EQUATOR network.

Results: From the methodological review analysis, information obtained indicates that 97% of the researches used direct observation and 3% indirect observation. On the other hand, 56.5% of the articles explain the instrument used and 77% justify the applied observational design. A quantitative comparison of the proportions was made in several methodological aspects, which resulted in only 15.21% reviewing the quality of the data, and that 67.3% of the articles contributed to the mixed methods approach. The methodological review allowed us to establish procedural profiles. The results indicate that 67% of the articles have been published in English, and of these, 77% were published in journals that have an impact factor. The majority of the researchers, 53.26%, belong to Spanish entities. The most studied substantive aspects were goal (34%), possession of the ball (28%), and corner (27%). The most observed events were Leagues, World Cups, individual players and other events.

Conclusions: The results obtained refer to both substantive and methodological aspects and allow us to configure a systematic review of mixed studies, in which we emphasize the aspects of a “systematic review” and a “mixed study,” within an integrated perspective.

Application of multivariant decision tree technique in high performance football: The female and male corner kick

The use of multidimensional statistical technique based on decision trees is of recent application in sports science. In the case of football, this technique has not yet been sufficiently proven. The aim of the present study was to search for different success models for the corners in the FIFA World Cup 2014 and FIFA Women's World Cup 2015. For this, the statistical analysis focused on the search for classification models for the different criteria considered (shot, shot between the three posts and goal), based on the creation of different decision trees that allow the most important variables to be identified quickly and efficiently. For this, 1117 corners were collected between the two competitions, performed in 116 international matches. It has been possible to establish multivariate models for the "shot" and "shot between the three posts" criteria, allowing, in some cases, to quadruple the potential for offensive success. On the other hand, we have been able to identify significant differences in the male and female model of execution. These findings suggest the need to continue deepening the study of tactical behavior in women's soccer from a multivariate perspective, and also propose a better optimization of the management and training of this type of actions for both male and female football. In addition, it has allowed to test the decision tree statistical technique in the analysis of high performance football, with satisfactory results and of great relevance in the applied field.

What Performance Analysts Need to Know About Research Trends in Association Football (2012-2016): A Systematic Review

BACKGROUND

Evolving patterns of match analysis research need to be systematically reviewed regularly since this area of work is burgeoning rapidly and studies can offer new insights to performance analysts if theoretically and coherently organized.

OBJECTIVE

The purpose of this paper was to conduct a systematic review of published articles on match analysis in adult male football, identify and organize common research topics, and synthesize the emerging patterns of work between 2012 and 2016, according to the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines.

METHODS

The Web of Science database was searched for relevant published studies using the following keywords: 'football' and 'soccer', each one associated with the terms 'match analysis', 'performance analysis', 'notational analysis', 'game analysis', 'tactical analysis' and 'patterns of play'.

RESULTS

Of 483 studies initially identified, 77 were fully reviewed and their outcome measures extracted and analyzed. Results showed that research mainly focused on (1) performance at set pieces, i.e. corner kicks, free kicks, penalty kicks; (2) collective system behaviours, captured by established variables such as team centroid (geometrical centre of a set of players) and team dispersion (quantification of how far players are apart), as well as tendencies for team communication (establishing networks based on passing sequences), sequential patterns (predicting future passing sequences), and group outcomes (relationships between match-related statistics and final match scores); and (3) activity profile of players, i.e. playing roles, effects of fatigue, substitutions during matches, and the effects of environmental constraints on performance, such as heat and altitude.

CONCLUSION

From the previous review, novel variables were identified that require new measurement techniques. It is evident that the complexity engendered during performance in competitive soccer requires an integrated approach that considers multiple aspects. A challenge for researchers is to align these new measures with the needs of the coaches through a more integrated relationship between coaches and researchers, to produce practical and usable information that improves player performance and coach activity.

Individual ball possession in soccer

This paper describes models for detecting individual and team ball possession in soccer based on position data. The types of ball possession are classified as Individual Ball Possession (IBC), Individual Ball Action (IBA), Individual Ball Control (IBC), Team Ball Possession (TBP), Team Ball Control (TBC) und Team Playmaking (TPM) according to different starting points and endpoints and the type of ball control involved. The machine learning approach used is able to determine how long the ball spends in the sphere of influence of a player based on the distance between the players and the ball together with their direction of motion, speed and the acceleration of the ball. The degree of ball control exhibited during this phase is classified based on the spatio-temporal configuration of the player controlling the ball, the ball itself and opposing players using a Bayesian network. The evaluation and application of this approach uses data from 60 matches in the German Bundesliga season of 2013/14, including 69,667 IBA intervals. The identification rate was F = .88 for IBA and F = .83 for IBP, and the classification rate for IBC was κ = .67. Match analysis showed the following mean values per match: TBP 56:04 ± 5:12 min, TPM 50:01 ± 7:05 min and TBC 17:49 ± 8:13 min. There were 836 ± 424 IBC intervals per match and their number was significantly reduced by -5.1% from the 1st to 2nd half. The analysis of ball possession at the player level indicates shortest accumulated IBC times for the central forwards (0:49 ± 0:43 min) and the longest for goalkeepers (1:38 ± 0:58 min), central defenders (1:38 ± 1:09 min) and central midfielders (1:27 ± 1:08 min). The results could improve performance analysis in soccer, help to detect match events automatically, and allow discernment of higher value tactical structures, which is based on individual ball possession.

A topography of free kicks in soccer

This study investigates the spatial relationship of performance variables for soccer free kicks. In order to suggest ways in which players might optimise their performance, we collected data from free kicks (<35 m to goal line) of two German Bundesliga seasons (2013/14, 2014/15) (n = 1624). In the analysis, we applied the ISO-map approach using colour gradients to visualise the mean values of a variable on a 2D-map of the pitch. Additionally, variograms were used to describe the degree of spatial dependence of the free kick variables. Results show that DENSITY, TYPE OF PLAY, PLAYERS IN WALL, DISTANCE TO WALL and RULE VIOLATION were strongly spatially dependent. Centrality and proximity to the goal increased the variables PLAYERS IN WALL, RULE VIOLATIONS and INTERRUPTION TIME, and the ratio of goals scored increased from 5.9% (central far) to 10.9% (central near). In 70.9% of the shots, players preferred a switched laterality, which did not result in a higher success rate. Furthermore, there was no statistical advantage for the defensive team when DISTANCE TO WALL was below 9.15 m or when there was a RULE VIOLATION. Crosses had a success rate (i.e., first controlled ball contact after the cross) of 20.8%. Played with natural laterality, they were 5% more successful than with switched laterality. Crosses from the right side outside the penalty box were 10% more successful than from the left side. Therefore, it might be worthwhile practising the defence of balls coming from this side.

The Influence of Referee Bias on Extra Time in Elite Soccer Matches

Referees have discretion over the addition of extra time at the end of the soccer game to compensate for lost time due to unusual stoppages. This study assesses if referees favor big teams by shortening close games where the big team is ahead and lengthening close games where the big team is behind. The sample comprises all 380 matches in the Spanish La Liga during the 2014-2015 season. The dependent variable was the extra time the referee decides to add to the second half. The independent variables were the score difference, opponent team's level of play, yellow cards, red cards, player substitutions, average attendance, and fouls committed. Linear regression analysis suggested that the greater the score difference between teams, the less extra time was added by the referee. However, in close games, referees tended to add more time for a higher level team when they were behind and add less time when they were ahead. Red cards and the number of fouls committed increased the extra time.

Evaluation of the match performances of substitution players in elite soccer

PURPOSE

To evaluate match performances of substitute players using different research designs.

METHODS

English Premier League matches were analyzed using a multiple-camera system. Two research designs were adopted: an independent-measures analysis comparing the match-performance characteristics of players completing the entire match (n = 810) vs substitutes (n = 286) and the players they replaced (n = 286) and a repeated-measures analysis comparing the same players completing full matches vs those in which they were introduced as a substitute (n = 94).

RESULTS

Most substitutions (P < .05) occurred at halftime and between the 60- to 85-min vs all first-half periods and the remaining second-half periods (effect size [ES]: 0.85-1.21). These substitutions become more (P < .01) offensive (eg, more attacking positions were introduced) in relation to the positions introduced as the half progressed (ES: 0.93-1.37). Independent-measures analysis indicated that high-intensity running was greater (P < .01) in substitutes compared with players who either completed the entire match or were replaced (ES: 0.28-0.67), but no differences were evident for pass-completion rates (ES: 0.01-0.02). Repeated-measures analysis highlighted that players covered more (P < .01) high-intensity running when they were introduced as substitutes compared with the equivalent period of the second- but not the first-half period (ES: 0.21-0.47). Both research designs indicated that attackers covered more (P < .05) high-intensity running than peers or their own performances when completing the entire match (ES: 0.45- 0.71).

CONCLUSIONS

Substitutes cover greater high-intensity-running distance; this was particularly evident in attackers, but pass-completion rates did not differ for any position. This information could be beneficial to coaches regarding optimizing the match running performances of their players, but much more work needs to be undertaken to investigate the overall impact of substitutes (physical, technical indicators, and contribution to key moments of matches).