Grant: Discovery Grants Program - Individual
Simon Fraser University
$31,000.00
Statistical Methods for Sports Analytics
EF 2024-25
Résumé
The following proposal does not involve Indigenous research.
With ever increasing data, the opportunities for investigating sports analytics problems have never been greater. In particular, many professional leagues now collect tracking data where the locations of players are recorded at a high rate (e.g., 10-24 times per second). Tracking data provide massive data sets where typically a million rows of observations are recorded per match in soccer. This contrasts with traditional box score data which provide only summary match statistics.
An immediate benefit of tracking data is that investigators can determine the movements of players at all times, even when they do not have the ball. The problems which we consider are of interest to sporting bodies (from the point of view of rules and injury), to teams (from the point of view of optimal performance), and also to casual fans. With our connections to national and provincial Canadian sports organizations, the research activities are important in providing a competitive advantage to Canadian teams.
The overarching long-term goal of my research progam is the development of statistical methods that aid in the advancement of sport. Toward this goal, my group will address short-term objectives over the next five years that involve study of three of the most popular sports in the world; tennis, soccer and hockey. In tennis, we have access to over 1.5 million serves in men's and women's professional tennis. With detailed knowledge of the results of each rally, we will develop hierarchical models appropriate for large datasets that describe match progression. Insights will be obtained with respect to player evaluation. In soccer, we are interested in the timing of corner kicks, a statistical event time analysis for which novel models are required to account for clustering patterns in the data. Improved understanding of corner kicks is relevant to soccer tactics. In hockey, we are interested in aging curves where typically a young player improves, reaches a plateau and then declines in performance in subsequent years. The construction of aging curves is a problem common to all sports and is important in terms of roster construction. A modelling challenge with aging curves is that data typically suffer from selection bias whereby the best players are over-represented in both tails of the age distribution.
The proposed methods are novel and translate to other domains in the natural sciences and engineering. For example, our investigation of the timing of corner kicks in soccer involves the realization of a mixture distribution where corner kicks following a corner kick occur more quickly on average than corner kicks following a stoppage in play; this is analogous to the timing of recurrent diseases in the biomedical sciences and also the timing of the recurrence of earthquakes in the environmental sciences.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2024-06557
Name nom
Swartz, Tim
Department département
Statistics and Actuarial Science - Statistics and Actuarial Science
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
31000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1508
Committee name en
Mathematics and Statistics
Committee name fr
Mathématiques et statistique
Area of application code
1205
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Mathematical sciences
Area of application fr
Sciences mathématiques
Research subject code
3004
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Applied statistics
Research subject fr
Statistique appliquée
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Statistical Methods for Sports Analytics
Keywords
sports analytics; statistical modelling; bayesian methods; prediction
Application summary
The following proposal does not involve Indigenous research.
With ever increasing data, the opportunities for investigating sports analytics problems have never been greater. In particular, many professional leagues now collect tracking data where the locations of players are recorded at a high rate (e.g., 10-24 times per second). Tracking data provide massive data sets where typically a million rows of observations are recorded per match in soccer. This contrasts with traditional box score data which provide only summary match statistics.
An immediate benefit of tracking data is that investigators can determine the movements of players at all times, even when they do not have the ball. The problems which we consider are of interest to sporting bodies (from the point of view of rules and injury), to teams (from the point of view of optimal performance), and also to casual fans. With our connections to national and provincial Canadian sports organizations, the research activities are important in providing a competitive advantage to Canadian teams.
The overarching long-term goal of my research progam is the development of statistical methods that aid in the advancement of sport. Toward this goal, my group will address short-term objectives over the next five years that involve study of three of the most popular sports in the world; tennis, soccer and hockey. In tennis, we have access to over 1.5 million serves in men's and women's professional tennis. With detailed knowledge of the results of each rally, we will develop hierarchical models appropriate for large datasets that describe match progression. Insights will be obtained with respect to player evaluation. In soccer, we are interested in the timing of corner kicks, a statistical event time analysis for which novel models are required to account for clustering patterns in the data. Improved understanding of corner kicks is relevant to soccer tactics. In hockey, we are interested in aging curves where typically a young player improves, reaches a plateau and then declines in performance in subsequent years. The construction of aging curves is a problem common to all sports and is important in terms of roster construction. A modelling challenge with aging curves is that data typically suffer from selection bias whereby the best players are over-represented in both tails of the age distribution.
The proposed methods are novel and translate to other domains in the natural sciences and engineering. For example, our investigation of the timing of corner kicks in soccer involves the realization of a mixture distribution where corner kicks following a corner kick occur more quickly on average than corner kicks following a stoppage in play; this is analogous to the timing of recurrent diseases in the biomedical sciences and also the timing of the recurrence of earthquakes in the environmental sciences.