Tell me how much your opponent team runs and I will tell you how much you should run : A predictive model applied to Spanish high-level football
Copyright © Biology of Sport 2024..
The aim of this study was to predict a team's accumulated distance (TotDisTea) and accumulated distance at > 21 km/h (TotDis21Tea) in the Spanish Football First Division. 2,946 team physical performances (out of 3040 possible) during four seasons (from 2016-17 to 2019-20) were analysed. The outcome variables were the TotDisTea and TotDis21Tea when the ball was in play. Eight predictor variables were used: the distance accumulated and accumulated at > 21 km/h by the opponent (TotDisOpp and TotDis21Opp) were registered in km, the effective playing (EffPlaTim) and possession (BalPos) time were recorded in min, match location (MatLoc) had two levels (home and away), match outcome (MatOut) had three levels (lost, drawn, and won), and the teams were grouped in four levels (Champions League, Europa League, remained, and relegation) distinguishing the observed team (TeaLev) and the opponent team (OppLev) in the match. A total of 127 models were estimated from the all-possible regressions procedure for each outcome variable. The model with six predictor variables was selected as the best model to predict the TotDisTea (R2adj = .82). The predictor variables TotDisOpp, EffPlaTim, and BalPos had a greater contribution to the mean outcome value than the predictors OppLev, TeaLev, and MatLoc. All models estimated to predict TotDis21Tea had little predictive power (R2adj < .38). The findings of this study have both theoretical and practical implications for practitioners. The interaction between teams has a great effect on the conditional response. Before the match, teams could use this information to anticipate the physical demand expected in the next match, and after the match, be able to assess whether the physical response was similar to expected, and make decisions.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:41 |
|---|---|
| Enthalten in: |
Biology of sport - 41(2024), 2 vom: 30. März, Seite 275-283 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Castellano, Julen [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Journal Article |
|---|
| Anmerkungen: |
Date Revised 26.03.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.5114/biolsport.2024.132984 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM370143795 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM370143795 | ||
| 003 | DE-627 | ||
| 005 | 20240327000226.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240326s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.5114/biolsport.2024.132984 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1349.xml |
| 035 | |a (DE-627)NLM370143795 | ||
| 035 | |a (NLM)38524806 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Castellano, Julen |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Tell me how much your opponent team runs and I will tell you how much you should run |b A predictive model applied to Spanish high-level football |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 26.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Copyright © Biology of Sport 2024. | ||
| 520 | |a The aim of this study was to predict a team's accumulated distance (TotDisTea) and accumulated distance at > 21 km/h (TotDis21Tea) in the Spanish Football First Division. 2,946 team physical performances (out of 3040 possible) during four seasons (from 2016-17 to 2019-20) were analysed. The outcome variables were the TotDisTea and TotDis21Tea when the ball was in play. Eight predictor variables were used: the distance accumulated and accumulated at > 21 km/h by the opponent (TotDisOpp and TotDis21Opp) were registered in km, the effective playing (EffPlaTim) and possession (BalPos) time were recorded in min, match location (MatLoc) had two levels (home and away), match outcome (MatOut) had three levels (lost, drawn, and won), and the teams were grouped in four levels (Champions League, Europa League, remained, and relegation) distinguishing the observed team (TeaLev) and the opponent team (OppLev) in the match. A total of 127 models were estimated from the all-possible regressions procedure for each outcome variable. The model with six predictor variables was selected as the best model to predict the TotDisTea (R2adj = .82). The predictor variables TotDisOpp, EffPlaTim, and BalPos had a greater contribution to the mean outcome value than the predictors OppLev, TeaLev, and MatLoc. All models estimated to predict TotDis21Tea had little predictive power (R2adj < .38). The findings of this study have both theoretical and practical implications for practitioners. The interaction between teams has a great effect on the conditional response. Before the match, teams could use this information to anticipate the physical demand expected in the next match, and after the match, be able to assess whether the physical response was similar to expected, and make decisions | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Match analysis | |
| 650 | 4 | |a Regression analysis | |
| 650 | 4 | |a Situational variables | |
| 650 | 4 | |a Team sports | |
| 650 | 4 | |a Time-motion | |
| 700 | 1 | |a López-Del Campo, Roberto |e verfasserin |4 aut | |
| 700 | 1 | |a Hileno, Raúl |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Biology of sport |d 1991 |g 41(2024), 2 vom: 30. März, Seite 275-283 |w (DE-627)NLM086731742 |x 0860-021X |7 nnns |
| 773 | 1 | 8 | |g volume:41 |g year:2024 |g number:2 |g day:30 |g month:03 |g pages:275-283 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.5114/biolsport.2024.132984 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 41 |j 2024 |e 2 |b 30 |c 03 |h 275-283 | ||