Data and Methods
Data source
This project uses a hockey player dataset packaged in the provided archive. The archive contains more than 100,000 player-dimension rows and more than 400,000 season-level rows, giving enough information to fit a multivariable statistical model with thousands of observations and more than 10 variables.
How the data was prepared
The analysis followed a simple workflow:
- cleaned the position labels into three main groups: Defense, Forward, and Goalie
- filtered out records that did not fit one of these groups
- calculated average and median height for each group
- visualized the results using a histogram, boxplot, and bar chart
Summary table
| Position group | Players | Average height | Median height |
|---|---|---|---|
| Defense | 30,064 | 184.0 cm | 183.0 cm |
| Forward | 54,023 | 181.0 cm | 180.0 cm |
| Goalie | 5 | 179.0 cm | 178.0 cm |