Analysis of substitution times in soccer

Silva, Rajitha M.; Swartz, Tim B.

doi:10.1515/jqas-2015-0114

Cited by 13 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the proposed rule was only followed in 34% of scenarios for potential application, losing teams improved their goal differential in 38-47% of cases when the rule was followed, compared with 17-24% of matches otherwise [33]. However, Silva and Swartz [38] criticised this approach as too simplistic, and considered a Bayesian logistic regression based upon a prior distribution in which team strength was related to the probability of the trailing team scoring the next goal.…”

Section: Patterns Of Introduction Of Soccer Substitutesmentioning

confidence: 99%

Profiling the Responses of Soccer Substitutes: A Review of Current Literature

et al. 2018

View full text Add to dashboard Cite

Depending upon competition regulations, the laws of soccer allow between three and an unlimited number of substitutions that can be made on either a permanent or rolling basis. Substitutes are typically introduced to minimise/offset the effects of fatigue, alter tactics, replace players deemed as underperforming or injured, and/or give playing time to youth players or to squad members returning from injury. While the match-day practices of substitutes include participation in the pre-match warm-up, and sporadic periods of rewarm-up activity, it is currently unclear as to whether these pre-entry preparations facilitate optimal match performance thereafter. Acknowledging the contextual factors that possibly influence substitutes' performance, this review summarises the presently available literature on soccer substitutes, and makes recommendations for future research. Literature searching and screening yielded 13 studies, which have typically focused on characterising: (1) the patterns, including timing, of substitutes' introduction; (2) indices of match-performance; and (3) the emotional experiences of soccer substitutes. The majority of substitutions occur after the first-half has ended (i.e. at half-time or during the second-half), with introduced players exceeding the second-half physical performances of those who started the match. Observations of progressive improvements in running performance as playing time increases, and findings that substitutes mostly experience negative emotions, highlight the potential inadequacies of pre-match preparations, and present future research opportunities. Additional work is therefore needed to confirm these findings and to determine the efficacy of current preparation strategies, thereby providing opportunities to assess then address substitutes' pre-pitch entry preparations, on-field performance and emotional responses.

show abstract

Section: Patterns Of Introduction Of Soccer Substitutesmentioning

confidence: 99%

Profiling the Responses of Soccer Substitutes: A Review of Current Literature

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Further, based on Figure 3, if one assumes that any stage i and stage i+1 are nearly identical situations in a match, handling such situations through a Bayesian approach with subjective priors can be considered as an avenue for future research. 24 The relatively similar prediction accuracy variation between the three classifiers suggest that we have potentially reached the maximum attainable prediction performance from the selected set of features. Thus, performing a further analysis with a different set of features may yield better performance results in terms of the prediction accuracy.…”

Section: Discussionmentioning

confidence: 83%

In-game winner prediction and winning strategy generation in cricket: A machine learning approach

Pussella

Silva

Egodawatta

2022

International Journal of Sports Science & Coaching

View full text Add to dashboard Cite

This study provides an in-game prediction of the winner for Twenty20 (T20) cricket by focusing on the matches played in the Indian Premier League. For the analysis, data were collected from 812 completed matches played between 2008 and 2020. Initially, several candidate features were identified, and then the LASSO method was applied as a feature selection technique to identify the most important set of features. Based on the identified important features, predictions are provided for each stage of a match where a T20 match can consist of a maximum of 240 stages. For each stage, three classification models were formed using Naive Bayes, Logistic Regression and Support Vector Machines. The prediction accuracy was used for evaluating the findings of the study, and the prediction accuracy of each model indicates the ratio between the number of correctly predicted instances and the total number of predicted instances. Naive Bayes demonstrated prediction accuracies ranging from 53.08% to 91.76% between the first and the 240th stage of matches, whereas the accuracy of Logistic Regression varied from 56.92% to 97.65%. In comparison, Support Vector Machines also displayed comparable outcomes with a prediction accuracy of 55.00% at the first stage, and 90.59% at the 240th stage. Furthermore, a strategy generator that assists the competing teams in the second innings to devise winning strategies, is presented in this study alongside an interactive web-based application for making in-game predictions, and for assisting the end users (players and coaching/managing staff) in decision making, based on the generated winning strategies.

show abstract

“…This idea has been used in the analysis of substitution times in soccer. 16 The additional parameter ρ is assumed independent of the remaining parameters and we assign ρ ∼ Uniform false( 0 , 1 false).…”

Section: A Bayesian Version Of the Cv-3 Modelmentioning

confidence: 99%

Bayesian approaches for critical velocity modelling of data from intermittent efforts

Peng

Clarke

Swartz

2022

International Journal of Sports Science & Coaching

View full text Add to dashboard Cite

In sports science, critical power and related critical velocity models have been widely investigated, and are being increasingly applied to field-based team sports. A challenge associated with these models is that laboratory experiments that yield accurate measurements of maximal sustainable velocity are expensive. Alternatively, inexpensive field data (from training and matches) are being used to fit such models. However, the intermittent nature of efforts in field-based sports implies that the dependent variable concerning maximum sustainable velocity is reliably calibrated only for short time durations. This paper develops methods where field data based on short time durations is combined with prior knowledge to fit the three-parameter critical velocity model. This is accomplished in a Bayesian framework for which Markov chain methods are required for model fitting and inference.

show abstract

Analysis of substitution times in soccer

Abstract: This paper considers the problem of determining optimal substitution times in soccer. We review the substitution rule proposed by Myers (Myers, B. R. 2012. “A Proposed Decision Rule for the Timing of Soccer Substitutions.”

Cited by 13 publications

References 9 publications

Profiling the Responses of Soccer Substitutes: A Review of Current Literature

Profiling the Responses of Soccer Substitutes: A Review of Current Literature

In-game winner prediction and winning strategy generation in cricket: A machine learning approach

Bayesian approaches for critical velocity modelling of data from intermittent efforts

Contact Info

Product

Resources

About