2025-11-02

Data Set

This project uses NFL_Injuries data set from kaggle

The data set looks at ACL, MCL, and concussion injuries in the Nation Football League throughout the 2012-2019 seasons

This data was cleaned from 4 separate tables into 1 table with 5 columns being year, injury type, season phase, amount occurred during practice, amount occurred during game, and total amounts.

Plotly 3D Plot

With this 3D plot we are able to see how the number of injuries compare to each other. Concussions are the most common of the three injuries and MCL injuries are more common than ACL injuries.

Bar Chart Code

To see if there is a proportional relationship for concussions during the preseason and regular season, a bar chart was used as a visual. The code below is for the bar chart of concussion injuries by year and season phase:

plot_ly(
  data = concuss,
  x = ~year,
  y = ~total,
  color = ~season_phase,
  type = "bar"
) %>%
  layout(
    barmode = "group",
    title = "Concussion Injuries by Year and Season Phase",
    xaxis = list(title = "Year"),
    yaxis = list(title = "Total Injuries"),
    legend = list(title = list(text = "Season Phase"))
  )

Grouped Bar Chart

Even with the preseason being about a month long compared to the 18 week regular season, most of the preseason injuries are close to the regular season concussion injuries.

Ggplot Trend Line

ACL injuries seem to have a smaller range compared to MCL injuries. This can be due to ACL injuries occurring via non contact and MCL happening through contact

Ggplot Trends Analyis

Ggplot Boxplot

Concussions are easily the most common injury pre and regular season. Yes, football is a contact sport and this statistic is the reason for many rule changes

Statisical Analysis

As a summary of the data, it shows like the majority of trends we saw that more concussion injuries occur throughout the regular season than the preseason. Concussions had a higher mean and a wider range meaning that due to competitiveness more concussion occur.

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    71.0    82.0   107.0   120.2   157.0   192.0
## # A tibble: 2 × 6
##   season_phase mean_injuries median_injuries sd_injuries min_injuries
##   <chr>                <dbl>           <dbl>       <dbl>        <int>
## 1 Preseason              81               81        5.95           71
## 2 Regular               160.             162       26.6           123
## # ℹ 1 more variable: max_injuries <int>