2018-2023 Badminton World Tour Points Head To Head

Histogram
Summary statistics
Side-by-side boxplots
Difference in means hypothesis test
Linear regression
Confidence interval for regression slope
Analyzing wins and points head to head in singles and doubles in the Badminton World Tour from 2018-2023.
Author

Abigail Smith

Published

June 26, 2024

Motivation

Badminton is a racket sport played by pairs (Doubles) or individuals (Singles). Badminton takes place on a court with a net in the middle separating the opponents. Players use rackets to hit a feathered ball known as the birdie across the net. Matches are won through the best of three games, each match is won by the first team to get 21 points. Points are won when the birdie hits the ground in the opposing side’s court.

While often considered a recreational sport, it is also played at the professional and Olympic level. The BWF Badminton World Tour is a tournament series with opens hosted in different countries around the world. The tour has been running since 2018 and even took place in 2020 despite the covid-19 pandemic. Statistics have been compiled from each World Tour, a notable statistic being the Points H2H which looks at the points for (pts_for) a player and the points against (pts_agst) them.

Through statistical analysis, patterns can be identified in this badminton dataset. Investigating the distribution of the Wins variable will highlight any patterns and what factors might impact winning in badminton at the World Tour Level.

Data

The data set has 185 rows with 9 variables. Each row is a player who participated in the World Tour. The data set has 5 years worth of data from 2018-2023, the players’ statistics are cumulative over the 5 years.

badminton.csv
Variable Description
Player The name of the player competing.
Category The category of competition the player competed in, either Singles or Doubles.
Matches The total number of matches the player played in between 2018-2023 in the World Tour.
Wins The total number of wins the player had between 2018-2023 in the World Tour.
Losses The total number of losses the player had between 2018-2023 in the World Tour.
pts_for The total number of points scored by the player between 2018-2023 in the World Tour.
pts_agst The total number of points allowed by the player between 2018-2023 in the World Tour.
win_pct The cumulative win percentage (Wins/Matches) for the player between 2018-2023 in the World Tour.
shot_pct The cumulative shot percentage (pts_for/(pts_for + pts_agst)) for the player between 2018-2023 in the World Tour.

Questions

  1. Create a histogram of Wins and describe the distribution.

  2. Obtain the summary statistics of Wins and fill them in below.

  3. Calculate the range for Wins and for pts_for.

  4. The ranges for Wins and pts_for are both quite large. What do you think is a possible reason for this flaw in the data?

  5. Create a side by side box plot of Wins for each Category. Describe the distribution.

  6. Perform a t.test to determine if there is a significant difference in the mean number of Wins for Doubles vs. Singles.

  7. Fit a simple linear model of pts_for predicting Wins.

  8. Interpret the slope of the model you just fit.

  9. If a player has 216 points calculate their predicted Wins.

  10. Assess the overall fit of the model.

  11. Find the 90% confidence interval of the slope of the model.

  12. Do you think that pts_for is really the most effective predictor of Wins? Why or why not? What could be a better predictor?

References

Original dataset from www.badmintonstatistics.net

Olympic Badminton Rules

BWF Tour Website