Sport Informatics and Analytics/Introductions

From WikiEducator
Jump to: navigation, search
Yass races, March 1936 - Sam Hood (2968464894).jpg



This is the first theme in our course. We are keen to introduce you to our approach to the open sharing of educational resources[1][2][3][4][5] and present some of the ideas central in a shift from "not invented here" to "proudly borrowed from there".[6]

Let them eat cake

Mine Cetinkaya-Rundel recommends a backward design approach to sharing course information. This is an exciting idea for those interested in non-linear learning. When this course was first written it was with a specific institution audience in mind. Since that time a great deal has changed.

We have explored Mine's ideas for this course and have an example of the approach using bicycle hire data. You can find the slide presentation at this link.

This theme

  • Explores our approach to open sharing and the narratives of such an approach.[7][8][9]
  • Introduces people, perspectives, products and processes in sport informatics and analytics.
  • Draws attention to an Informatik tradition and its links with sport informatics.
  • Discusses the emergence of sport analytics.
  • Explores microlearning.

In addition to this introduction, the course includes these topics as part of this theme:


We are mindful that throughout this course we must be sensitive to what is to count as evidence, how we record data[10][11][12][13], our objectivity in the analysis of performance[14][15][16][17][18], including how we address objective reality[19][20], and evidence-based practice.[21] We need to be clear too about how we use the terms reproducibilty and replicability in our research and practice.[22][23]

Thomas Kelly[24] provides an introduction to the concept of evidence and notes:

‘Evidence’ is hardly a philosopher's term of art: it is not only, or even primarily, philosophers who routinely speak of evidence, but also lawyers and judges, historians and scientists, investigative journalists and reporters, as well as the members of numerous other professions and ordinary folk in the course of everyday life.[25]

Kevin Gray[26], amongst others, points out that all evidence is not equal and can differ in quantity and quality. He raises a fundamental issue for anyone involved in sport informatics and analytics:

Some results can be calculated precisely or are determined by rules. Others can be estimated probabilistically with statistics and machine learning tools. However, decision-makers are often confronted with situations in which they must rely on their gut.[27]

We encourage you to reflect on the decisions you make about evidence (including the contents of this course) as you analyse performance. These may be decisions that are:

  • Deterministic (results can be calculated precisely or are determined by rules)
  • Probabilistic (estimated probabilistically with statistics and machine learning tools)
  • Intuitive (reliance on 'gut instinct')

These three approaches are interconnected in informatics and analytics in the ethical decisions[28] we make about our practice and inform our work as an analyst "to reconcile conflicting ideas while still producing something useful".[29]

A good starting point for our reflections about evidence is Kevin Gray's observation "humans frequently misconstrue conjecture as evidence. We also readily reject evidence that contradicts our opinions, and cherry-pick data and analytics to support decisions we’ve already made".[30]

As we consider what is to count as evidence, it might be helpful to revisit William Deming's (1975)[31] paper to contemplate how we assign probability to evidence. In the paper, William distinguishes between enumerative ("an estimate of the number of units of a frame that belong to a specified class"[32]) and analytical ("a basis for action on the cause-system or the process, in order to improve product of the future"[33]) approaches. William adds:

The basic supposition here is that any statis­tical investigation is carried out for purposes of action. New knowledge modifies existing knowledge.[34]

As David Yarrow and Matthias Kranke (2016)[35] indicate, such action is not exclusively objective and value neutral. They suggest that a critical, interdisciplinary performative understanding of statistics enables "an unpacking of the socio-material mechanisms through which data-heavy analytical technologies shape processes of valuation, commercialisation and regulation"[36] in sport. This understanding recognises, as Jeff Leek (2017) suggests, "data analysis is not purely computational and algorithmic — it is a human behaviour"[37] and that when we share evidence we must be conscious of the narrative we use to discuss about our findings.[38][39]

Galit Shmueli (2010)[40] proposes that when we construct narratives we must distinguish between explanation and prediction. (See also, her discussion of description (2018)[41] in statistical modelling.)

We might reflect also on the the contextual intelligence[42] we bring to our practice of observing and analysing performance in sport. This reflection could include 'good enough practices in scientific computing'[43], the role of a data analyst as an artist[44], wanderer[45], our relationship to data humanism[46] and an awareness of confirmation bias.[47]

Martin Fowler (2015)[48] has written about the volume of data that is now available. He identified the appearance of a data lake as an idea "to have a single store for all of the raw data that anyone in an organization might need to analyze". The data lake stores raw data, in whatever form the data source provides. James Dixon (2010)[49] introduced the concept of a data lake when he observed "the traditional solutions we have created a concept called the Data Lake to describe an optimal solution". He added that the "contents of the data lake stream in from a source to fill the lake, and various users of the lake can come to examine, dive in, or take samples".

Martin Fowler (2015)[50] observed:

It is important that all data put in the lake should have a clear provenance in place and time. Every data item should have a clear trace to what sformatystem it came from and when the data was produced. The data lake thus contains a historical record.

Informatik and informatics

In this course, we acknowledge the connection between informatik and informatics. In your reading, you will come across a number of terms used to describe how we live with information in a digital age.[51]

Karl Steinbuch[52] used the term informatik ("die automatische Dataverarbeitung wir nennen sie heute informatik") in a 1957 paper that became the German term for computer science[53][54]. For more information about the emergence of the Informatik tradition you might like to look at Daniel Link and Martin Lames' (2009) paper.[55]

In 1962, Philippe Dreyfus created the French term l'informatique as a combination of information and automatique[56]. In 1966, L'Academie française defined 'l'informatique' as:

Science du traitement rationnel, notamment par des machines automatiques, de l' information considérée comme le support des connaissances humaines et des communications dans les domaines techniques, économiques et sociaux.[57]

In the same year as Philippe Dreyfus used l'informatique, Walter Bauer, Werner Frank, Richard Hill and Frank Wagner formed the Informatics company in the United States of America, to contribute to the "science of information handling"[58].

In 1963, F.E. Temnikov produced a paper titled Informatika. Three years later, A.I. Mikhailov, A.I. Chernyl and R.S. Gilyarevski used the word Informatika as the name for the theory of scientific information[59].

Each of these terms, created in their own cultural contexts, described activities that:

are essentially the everyday activities that have been enacted throughout history and across cultures: selecting, communicating, discovering, recording, organising, problem-solving, deciding and learning.[60]

Daniel Link and Martin Lames (2009)[61] provide a detailed account of the origins of sport informatics in Germany. They note that:

The term covers all activities at the interface of computer science and sport science, ranging from simple tools for handling data and controlling sensors on to the modelling and simulation of complex sport-related phenomena.[62]

Examples of where the informatik tradition has led researchers and practitioners can be found in Daniel Memmert and Dominik Raabe's (2017)[63] Revolution im Profifußball.

Arnold Baca (2006)[64] provides an introduction to the emergence of Sportinformatik.

Sport analytics

In the last two decades there has been a gradual change in how we refer to the observation, recording and analysis of performance in sport. We tend to hear and read less about notational analysis now and talk more about analytics[65][66]. This indicates an important change in the community of practice that analyses performance in sport[67][68]. Jay Coleman (2012)[69] identifies some of the 'players' in sports analytics research. Bill Gerard (2015[70] has provided an overview of this change in the community. Felix Lebed (2017)[71] locates this change in the context of the discipline of analytics. Erin Wasserman and her colleagues (2018)[72] provide an overview of the fundamentals of sport analytics. Jacquie Tran (2019)[73] shared her macro view of sports analytics.

In 2005, the Journal of Quantitative Analysis in Sports appeared "as the first academic journal dedicated to statistical analysis in sports"[74]. There was an announcement in 2019 for the Journal of Sport Analytics[75] as "a new high-quality research journal that aims to be the central forum for the discussion of practical applications of sports analytics research, serving team owners, general managers, coaches, fans, and academics".

Benjamin Alamar and Vijay Mehrotra (2011)[76] define sport analytics as:

the management of structured historical data, the application of predictive analytic models that utilize that data, and the use of information systems to inform decision makers and enable them to help their organizations in gaining a competitive advantage on the field of play.

Their definition has three components: data management; predictive models; and information systems.

Thomas Davenport and Jeanne Harris (2007)[77] proposed that analytics are a subset of business intelligence. They defined analytics as:

The extensive use of data, statistical and quantitative analysis, explanatory and predictive models, and fact-based management to drive decisions and actions. The analytics may be input for human decisions or may drive fully automated decisions. (2007:7)

In 2014, Chris Anderson proposed that sport analytics is:

The discovery, communication, and implementation of actionable insights derived from structured information in order to improve the quality of decisions and performance in an organization.

Chris's definition refers to actionable insights. This is a component of Adam Cooper's (2012) wide ranging definition of analytics as:

Analytics is the process of developing actionable insights through problem definition and the application of statistical models and analysis against existing and/or simulated future data.[78]

More recently, Bill Gerard (2016)[79] argues for "a narrow definition of sports analytics" as the analysis of tactical data to support tactics-related sporting decisions. He suggests "this narrow definition captures the uniqueness and the innovatory nature of sports analytics as the analysis of tactical performance data."

Felix Lebed (2017)[80] has extended the discussion about sport analytics through "the prism of the complexity approach to all human subjects of games playing, training, coaching and managing".[81]

Patrick Ward, Johann Windt and Thomas Kempton (2019)[82] draw attention to business intelligence opportunities for sport scientists "to develop systematic analysis frameworks to enhance performance within their organisation". These opportunities combine data collection and organisation, analytic models to drive insight and interface through communication.

Rasmus Jørnø and Karsten Gynther (2018)[83] discuss actionable insights (in learning analytics). You might find their paper of interest as you explore the relationships between observation, analysis and decision-support in sport analytics.

Video signpost

Our Introductions theme is presented by Trent Hopkinson.


The theme overview provides a framework to our approach to Sport Informatics and Analytics.

There is a slide presentation.

There is a mind map for this theme that includes resources up to 2015. For more recent resources (2016 onward) see this site.

There is more background information about Informatics and Analytics on this wiki.

There are some video suggestions. (See slides 2-4)

Daniel Link's (2009) presentation Interdisciplinarity in Sport Informatics.

There are some additional resources.

Introductory activities

Icon activity line.svg
By way of an introduction

We thought you might like to start with an example of the use of analytics insights in sport. Dave Carolan (2019)[84] shared his experiences of two decades in association football in England in a thirty-five minute video recording. We hope this gives an explicit example of the changes in one sport from someone involved closely in the sport over a long period of time.

The video has six sections:

  • In The Beginning (02:40 on the video timeline)
  • 1998-2002: Enlightenment (08:45)
  • 2003-2011: Establishment (16:30)
  • 2012-2018: Engagement (21:05)
  • The Future: What Awaits? (24:12)
  • What issues persist for the industry? (29:05)

We wonder whether this time sequence might be common to all sports. What do you think?

Icon activity line.svg
How much information do you need?

In the Evidence section of this introduction to the course, we encouraged you to reflect on the decisions you make about evidence (including the contents of this course) as you analyse performance. As a start to that process, we suggest you have a look at Ian Levy's (2018)[85] discussion of the basketball player Joel Embiid. The first two paragraphs of Ian's article are:

Joel Embiid’s rookie season was dynamite. After waiting two injury-riddled seasons to make his NBA debut, Embiid came out with per-36 minute averages of 28.7 points, 11.1 rebounds, 3.0 assists, 1.2 steals and 3.5 blocks, shooting 46.6 percent from the field and 36.7 percent from beyond the arc. It was thoroughly dominating.

The counterpoint to those numbers, of course, was that Embiid never actually played 36 minutes in any of the 31 games in which he appeared, none of which came after the end of January. Embiid played just 786 minutes across the entire season and, as good as he looked on the court, it was reasonable to wonder if his incredible numbers were inflated at some level by small sample size.

What insights does Ian's article give you about Joel's performance? How might you go about collecting information about a single player?

Icon activity line.svg

Now that you have reflected on the decisions you make about evidence (including the contents of this course) as you analyse performance, we wondered if you might like to contemplate what we mean by 'data'. We recommend you look at Sandra Rendgen's (2018) discussion of what constitutes data [86] as a way to clarify your own thoughts about data in a digital age. You might find the issues raised by Rafael Irizarry (2018)[87], Jennifer Thompson (2018)[88] and Stephanie Hicks (2018)[89] of interest too.

You might find RStudio's (2019)[90] account of learning data science of interest as you explore how to "data acquisition and wrangling, exploratory data analysis, data visualization, and effective communication".

Icon activity line.svg
What is sport analytics?

In the Sport analytics section of this introduction to the course, we outlined some characteristics of sport analytics. In order to explore the practice of sport analytics, we suggest you look at Garry Gelade's (2018a)[91] discussion of sport analytics as a decision support system. In his post, Garry identifies four Is of analytics: information, intelligence, insight and impact. Garry discusses these in the context of his work in association football. What do you make of Garry's discussion about the impact of the analytics process on coach and athlete behaviour? You might extend your consideration of these issues with reference to Garry's discussion of the use of spatial metrics in association football (2018b)[92].

For a specific discussion of sport analytics in practice, see Dinny Navaratnam's (2019)[93] account of the role of a senior analyst at an Australian Rules Football club, St. Kilda.

You might also find the Bruce Schoenfeld's (2019)[94] discussion of analytics at Liverpool football club of interest too.

ePortfolio questions

Icon reflection line.svg
Questions about this theme

As you work your way through this theme you might like to consider these six questions.

Q1. What are your thoughts about a non-linear course in which you are the driver of your own learning pathway?

Q2. How might we help you to connect with others on the course?

Q3. Do you have any resources you would like to recommend for inclusion in the course?

Q4. Is there a difference between Informatik and Informatics?

Q5. What distinguishes Sport Analytics from Sport Informatics?

Q6. What is the relationship between Informatik, Informatics, Analytics and Performance Analysis?


  1. Jonathan Tennant et al. "The academic, economic and societal impacts of Open Access: an evidence-based review", 2016. Retrieved on 13 May 2016.
  2. Hilton, John; Wiley, David; Stein, Jarred; Johnson, Aaron (2010). "The four ‘R’s of openness and ALMS analysis: frameworks for open educational resources". Open Learning 25(1): 37-44.
  3. Stephen Downes "Applications, Algorithms and Data: Open Educational Resources and the Next Generation of Virtual Learning", 30 November 2017. Retrieved on 14 December 2017.
  4. Stephen Downes "E-Learning 3.0, Part 1: Data", 26 October 2018. Retrieved on 8 November 2018.
  5. Stephen Downes "A Quick Look at the Future of OER", 5 March 2019. Retrieved on 7 March 2019.
  6. Cited by Cable Green of Creative Commons during presentations. See for example:
  7. Alan Levine [1], 29 April 2019. Retrieved on 3 May 2019.
  8. Stephen Downes [2], 11 June 2019. Retrieved on 13 June 2019.
  9. Stephen Downes [3], 16 Otober 2019. Retrieved on 18 October 2019.
  10. Wickham, Hadley (2014). "Tidy Data". Journal of Statistical Software 59: https://10.18637/jss.v059.i10.
  11. Broman, Karl; Woo, Kara (2018). "Data Organization in Spreadsheets". The American Statistician 72(1):
  12. Lambert, Phil (16 February 2020). [Evidence is the new catchword in education, but it requires some scrutiny "Philosophers On a Physics Experiment that “Suggests There’s No Such Thing As Objective Reality: A Commentary”"]. Evidence is the new catchword in education, but it requires some scrutiny. Retrieved 26 February 2020.
  13. Weinberg, Justin (21 March 2019). "Philosophers On a Physics Experiment that “Suggests There’s No Such Thing As Objective Reality”". Retrieved 23 March 2019.
  14. van Bommel, Matthew; Bornn, Luke (2017). "Adjusting for scorekeeper bias in NBA box scores". Data Mining and Knowledge Discovery 31(6): 1622-1642.
  15. Wright, Jack (9 April 2018). "Rescuing Objectivity: A Contextualist Proposal". Philosophy of the Social Sciences
  16. Lancaster, James (20 April 2018). "What might appear to be common sense is not always based on scientific evidence". Retrieved 20 April 2018.
  17. Aschwanden, Christine; Nguyen, Mai (18 May 2018). "How Shoddy Statistics Found A Home In Sports Research". Retrieved 21 May 2018.
  18. Lancaster, James (20 July 2018). "Data-Driven? Think again". Retrieved 22 July 2018.
  19. Downes, Stephen (22 March 2019). "Philosophers On a Physics Experiment that “Suggests There’s No Such Thing As Objective Reality: A Commentary”". Retrieved 23 March 2019.
  20. Weinberg, Justin (21 March 2019). "Philosophers On a Physics Experiment that “Suggests There’s No Such Thing As Objective Reality”". Retrieved 23 March 2019.
  21. McKnight, Lucinda; Morgan, Andy (2019). "A broken paradigm? What education needs to learn from evidence-based medicine". Journal of Educational Policy
  22. Leek, Jeffrey; Peng, Roger (2015). "Opinion: Reproducible research can still be wrong: Adopting a prevention approach". Proceedings of the National Academy of Sciences 112(6): 1645-1646.
  23. Ellis, Shannon; Leek, Jeffrey (2018). "How to share data for collaboration". The American Statistician 72(1): 53-57.
  24. Kelly, Thomas (13 October 2009). "Evidence". Retrieved 25 July 2017.
  25. Kelly, Thomas (2014). "Evidence". Retrieved 13 October 2017.
  26. Gray, Kevin (23 May 2017). "Who Cares About Evidence?". Retrieved 13 October 2017.
  27. Gray, Kevin (23 May 2017). "Who Cares About Evidence?". Retrieved 13 October 2017.
  28. Manifesto for Data Practices (2018). "Manifesto for data practices". Retrieved 18 February 2018.
  29. Peng, Roger (18 June 2018). "The Role of Resources in Data Analysis". Retrieved 7 July 2018.
  30. Gray, Kevin (23 May 2017). "Who Cares About Evidence?". Retrieved 13 October 2017.
  31. Deming, William (1975). "On probability as a basis for action". The American Statistician 29(4): 146-152.
  32. Deming, William (1975). "On probability as a basis for action". The American Statistician 29(4): 146.
  33. Deming, William (1975). "On probability as a basis for action". The American Statistician 29(4): 146.
  34. Deming, William (1975). "On probability as a basis for action". The American Statistician 29(4): 146.
  35. Yarrow, David; Kranke, Matthias (2016). "The performativity of sports statistics: towards a research agenda". Journal of Cultural Economy 9(5): 445-457.
  36. Yarrow, David; Kranke, Matthias (201). "The performativity of sports statistics: towards a research agenda". Journal of Cultural Economy 9(5): 445.
  37. Leek, Jeff et al (28 November 2017). "Five ways to fix statistics". Retrieved 29 November 2017.
  38. Myint, Leslie; Leek, Jeffrey; Jager, Leah (2017). Explanation implies causation?.
  39. McShane, Blakeley et al (2017). Abandon Statistical Significance.
  40. Shmueli, Galit (2010). "To Explain or to Predict?". Statistical Science 25(3): 289-310.
  41. Shmueli, Galit (2017). "Statistical modeling in 3D: Describing, Explaining and Predicting". Retrieved 16 July 2018.
  42. Brown, Charles; Gould, Dan; Foster, Sandra (2005). "A framework for developing contextual intelligence (CI)". The Sport Psychologist 19(1): 51-62.
  43. Greg et al, Wilson. "Good enough practices in scientific computing". PLoS Comput Biol 13(6):
  44. Peng, Roger & Matsui, Elizabeth (26 April 2017). "The Art of Data Science". Retrieved 4 April 2018.
  45. Ranzolin, David (19 January 2018). "The Data Analyst as Wanderer: Pre-Exploratory Data Analysis with R". Retrieved 17 March 2018.
  46. Lupi, Giorgio (17 February 2017). "Data Humanism". Retrieved 27 March 2018.
  47. Nickerson, Charles; Raymond. "Confirmation Bias: A Ubiquitous Phenomenon in Many Guises". Review of General Psychology 2(2): 175-220.
  48. Fowler, Martin (5 February 2015). "DataLake". Retrieved 18 October 2019.
  49. Dixon, James (14 October 2010). "Pentaho, Hadoop, and Data Lakes". Retrieved 18 October 2019.
  50. Fowler, Martin (5 February 2015). "DataLake". Retrieved 18 October 2019.
  51. Ione, Amy (2018). A Mind at Play: How Claude Shannon Invented the Information Age. New York: Simon and Schuster.
  52. Steinbuch, Karl (1957). "Informatik: Automatische Informationsverarbeitung". SEG-Nachrichten (Technische Mitteilungen der Standard Elektrik Gruppe)–Firmenzeitschrift 4: 171.
  53. Widrow, Bernard et al (2005). "Karl Steinbuch 1917-2005". IEEE Computational Intelligence Society August: 5.
  54. Ernst, Hartmut; Schmidt, Jochen; Beneken, Gerd (2015). "Einführung". Grundkurs Informatik: 1-36.
  55. Link, Daniel; Lames, Martin (2009). "Sport Informatics – Historical Roots, Interdisciplinarity and Future Developments". International Journal of Computer Science in Sport 8(2): 68-87.
  56. Paoletti, Felix (1993). "Epist´emologie et technologie de l’informatique". Revue de l’EPI (Enseignement Public et Informatique): 175-182.
  57. Paoletti, Felix (1993). "Epist´emologie et technologie de l’informatique". Revue de l’EPI (Enseignement Public et Informatique): 176.
  58. Bauer, Walter (2007). "Computer Recollections: Events, Humor, and Happenings". IEEE Annals of the History of Computing 29(1): 85-89.
  59. dos Santos, Robert (2007). "Analise da terminologia soviética “Informatika” e da sua utilização nas décadas de 1960 e 1970".
  60. Gammack, John; Hobbs, Valerie; Pigott, Diarmuid (2007). The Book of Informatics. Melbourne: Cegage Learning Australia. p. 19.
  61. Link, Daniel; Lames, Martin (2009). "Sport Informatics–Historical Roots, Interdisciplinarity and Future Developments". International Journal of Computer Science in Sport 2: 68-87.
  62. Link, Daniel; Lames, Martin (2009). "Sport Informatics–Historical Roots, Interdisciplinarity and Future Developments". International Journal of Computer Science in Sport *(2): 69.
  63. Memmert, Daniel; Raabe, Dominik (Eds) (2017). Revolution im Profifußball: Mit Big Data zur Spielanalyse 4.0. Berlin: Springer-Verlag.
  64. Baca, Arnold (2006). "Computer science in sport: an overview of history, present fields and future applications (part I).". International Journal of Computer Science in Sport, 4(1): 25-31.
  65. Link, Daniel (2017). "Sports Analytics". German Journal of Exercise and Sport Research
  66. Emerging Technology (7 March 2016). "Big Data Analysis Is Changing the Nature of Sports Science". Retrieved 4 May 2018.
  67. Stein, Manuel et al (2017). "How to Make Sense of Team Sport Data: From Acquisition to Data Modeling and Research Aspects". Data 2(1): 2.
  68. Portch, John (18 February 2019). "How Manchester City Translate Data into Meaningful Interventions". Retrieved 19 February 2019.
  69. Coleman, Jay (2012). "Identifying the 'players' in sports analytics research". Interfaces 42(4): 109-118.
  70. Gerrard, Bill (2015). "Analytics, Technology and High Performance Sport". Retrieved 9 November 2017.
  71. Lebed, Felix (2017). Complex Sport Analytics. Abingdon: Routledge.
  72. Wasserman, Erin et al (2018). "Fundamentals of Sports Analytics". Clinics in sports medicine 37(3): 387-400.
  73. Tran, Jacquie (6 February 2019). "A macro view of sports analytics". Retrieved 7 February 2019.
  74. Alamar, Benjamin (2005). "A First Step". Journal of Quantitative Analysis in Sports 1(1).
  75. "A First Step". Aims and Scope: Journal of Sport Analytics in Sports. 2019.
  76. Alamar, Benjamin; Mehrotra, Vijay (2011). "Beyond ‘Moneyball’: Rapidly evolving world of sports analytics, Part I". Retrieved 9 November 2017.
  77. Davenport, Thomas; Harris, Jeanne (2007). Competing on Analytics: The New Science of Winning. Boston: Harvard Business School Press.
  78. Cooper, Adam (2012). "What is analytics? Definition and essential characteristics". CETIS Analytics Series 1(5): 1-10.
  79. Gerrard, Bill (22 June 2016). "Understanding Sports Analytics". Retrieved 9 November 2017.
  80. Lebed, Felix (2017). Complex Sport Analytics. Abingdon: Routledge.
  81. Lebed, Felix (2017). Complex Sport Analytics. Abingdon: Routledge. p. xix.
  82. Ward, Patrick; Windt, Johann; Kempton, Thomas (2019). "Business Intelligence: How Sport Scientists Can Support Organisation Decision Making in Professional Sport". International journal of sports physiology and performance doi: 10.1123/ijspp.2018-0903.
  83. Jørnø, Rasmus; Gynther, Karsten (2018). "What Constitutes an ‘Actionable Insight’in Learning Analytics?". Journal of Learning Analytics 5(3): 198-221.
  84. Carolan, Dave (19 February 2019). "Two Decades of Sports Science in Football". Retrieved 19 February 2019.
  85. Levy, Ian (26 March 2018). "Nylon Calculus: Joel Embiid has your sample size right here". Retrieved 27 March 2018.
  86. Rendgen, Sandra (2018). "What do we mean by “data”?". Retrieved 24 June 2018.
  87. Irizarry, Rafael (1 November 2018). "The role of academia in data science education". Retrieved 2 November 2018.
  88. Thompson, Jennifer (31 October 2018). "The Data Person as Project Manager". Retrieved 2 November 2018.
  89. Hicks, Stephanie (15 October 2018). "Importance of Skepticism in Data Science". Retrieved 2 November 2018.
  90. RStudio (2019). "Data Science in a Box". Retrieved 12 July 2019.
  91. Gelade, Garry (19 February 2018). "Analytics as a decision support system". Retrieved 19 April 2018.
  92. Gelade, Garry (22 October 2018). "Journey into Space: Using spatial metrics to compare and cluster football players". Retrieved 24 October 2018.
  93. Navaratnam, Dinny (21 March 2019). "Number crunch: Datahead 'DOS' revolutionising football analysis". Retrieved 22 March 2019.
  94. Schoenfeld, Bruce (22 May 2019). "How Data (and Some Breathtaking Soccer) Brought Liverpool to the Cusp of Glory". Retrieved 23 May 2019.