Basic statistic
1. Why Statistics Matter in Football
Helps analyze data like goals, wins, and penalties.
Turns football knowledge into structured insight.
2. Key Concepts
a. Variables and Cases
Variables: Features or characteristics (e.g., goals scored, age, height).
Cases: The subjects being studied (e.g., players, teams).
b. Example
Player data: Age, height, goals = variables; players = cases.
Team data: City, shirt color, goals scored = variables; teams = cases.
3. Variables vs Constants
A variable must vary (e.g., team city).
A constant stays the same across cases (e.g., country = Spain for all Spanish teams).
4. Levels of Measurement
Level
Nominal
Ordinal
Description
Categories without order
Categories with a meaningful order
Example
Nationality, city, gender
League rankings (1st, 2nd, 3rd)
Interval
Ratio
Ordered, equal spacing, no true zero
Like interval + meaningful zero point
Age (18, 19, etc.)
Height, number of goals
5. Types of Variables
Categorical: Nominal + Ordinal
Quantitative: Interval + Ratio
Basic statistic
6. Discrete vs Continuous Variables
Discrete: Countable values (e.g., goals: 0, 1, 2…)
Continuous: Infinite values within a range (e.g., height: 170.2 cm)
7. Importance of Measurement Levels
The type of analysis depends on how variables are measured.
In practice, ordinal variables with many categories (e.g., rating 0–10) can be treated as
quantitative.
8. Final Takeaway
Thinking in terms of cases, variables, and measurement levels helps you become a
better football analyst.
It structures your understanding and prepares you for deeper statistical analysis.
Basic statistic
Summary: Organizing and Presenting Data in a Statistical Study
1. Cases and Variables
Cases: The individuals or items being studied (e.g., football players).
Variables: Characteristics of those cases (e.g., age, weight, goals).
2. Data Matrix
A data matrix organizes all your data.
o Rows = cases (e.g., Player 1 to Player 400).
o Columns = variables (e.g., age, weight, team).
o Cells = observations (e.g., Player 7 weighs 80.3 kg).
3. Incomplete Data
Some cells may be missing (e.g., missing weight or age).
These incomplete cases may need to be removed for certain analyses.
4. Purpose of the Data Matrix
Used for all statistical analyses.
Not typically shown to others due to its size and complexity.
5. Summarizing Data
Use tables and graphs to present findings clearly.
6. Frequency Table (for Categorical Variables)
Shows how many cases fall into each category.
Example: Hair color (blond, brown, black, other).
Includes:
o Absolute frequencies (number of players)
o Relative frequencies (percentages)
o Cumulative percentages (totals up to a point)
Basic statistic
7. Handling Quantitative Variables
A direct frequency table is not useful for continuous variables (e.g., weight).
Solution: Recode values into interval categories (e.g., 60–69.9 kg).
o This simplifies the data.
o Turns a quantitative variable into an ordinal variable.
8. Recode Limitations
You can recode quantitative → ordinal.
You cannot recode ordinal → quantitative.
9. Key Takeaways
Use a data matrix to store all data for analysis.
Use summaries (tables/graphs) for sharing results.
Frequency tables are effective for categorical data.
For quantitative variables, recoding into intervals helps in presentation.