The use of data in sports analytics is becoming more and more popular as new methods are discovered each day. Today, we will discuss the application of frequency distribution in sport analytics. In frequency distribution techniques, coaches and analysts employ the use of a frequency table to organize data. This table provides information such as number of games played, number of wins and losses and scoring statistics. A frequency table is a typical win/loss chart.
Why frequency distribution methods?
A frequency table provides information in a manner that can be easily read and understood. Users can simply read along the row for the desired information.
In the frequency table, there are columns for number of wins and percentage of wins. The number of wins indicate the frequency of wins and the percentage of wins is the relative frequency.
Relative frequency is calculated by dividing the total number of wins (of a team e.g. football team) by the total number of games played. This way, discrepancies in the number of games played per team are not seen, thus making it easier to compare the teams in question.
Frequency tables measure qualitative (non-numerical) or quantitative (numerical) data. Qualitative, also called categorical data are described as discrete variables – they have limited number of outcomes and cannot be ranked. Number of wins is discrete, meaning that they are whole numbers as you cannot have 3.5 or 1.5 wins.
Qualitative variables can be either discrete or continuous. Continuous variables can take on any value, whole number or not. For example, the weight of a wrester is a continuous variable as a wrestler can be 190 or 190.5 pounds.
Frequency tables are usually viewed in the form of graphs, called histograms.
Histograms make it easier to compare disparate data and look for similar patterns. They can be presented by shapes, the normal or bell curve (like the shape of a bell). The normal curve is interpreted as what happens theoretically under ideal conditions. Therefore, no data will ever form an exact bell curve.
Frequency tables or histograms can be compared by examining their symmetries. Normal distributions are completely symmetrical with the mode, or highest point, in the middle. When the highest point is facing the left side of the graph, the graph is said to be positively skewed and if the highest point is towards the right side, it is negatively skewed.
Frequency tables and histograms have proven to be a quick and convenient way for sports analysts and teams to compare individual players as well as teams.
This method can also be used to compare the stats of a single player. For example, numbers of yards per pass for a quarterback can be listed by category such as 0 to 5 yards, 6 – 10 yards, 10-15 yards etc. The use of a histogram chart is also a helpful visual to better illustrate the strength and weaknesses of a team.