Introduction to the data

This data set includes statistics from the 2021-2022 football season for the top 300 players in terms of fantasy points scored. Fantasy football is an online game in which you draft a team of players from throughout the National Football League and compete against people within your league. The points scored are based on ESPN’s scoring method of categorizing how many points each individual statistic gets for a player. For example, a rushing or receiving touchdown is worth 6 points, 10 rushing yards are worth 1 point, etc. The variables in this set are listed and explained below:

• Fantasy Rank (The rank of each Fantasy Player based on points scored)

• Name (Name of the player)

• Team (Team that the player is on)

• Position (Position the player plays)

• Games Played (Number of games the player played in throughout the season)

• Pass_YDS (how many passing yards a player had at the end of the season)

• Pass_TD (how many passing touchdowns a player had at the end of the season)

• INT (how many interceptions a player had at the end of the season)

• Rush_YDS (how many rushing yards a player had at the end of the season)

• Rush_TD (how many rushing touchdowns a player had at the end of the season)

• REC (how many receptions a player had at the end of the season)

• REC_YDS (how many receiving yards a player had at the end of the season)

• Fumbles (how many fumbles a player had at the end of the season)

• Points Per Game (how many points per game a player scored)

• Total Fantasy Points (how many receptions a player had at the end of the season)

• injurystatus (dummy variable showing whether or not the player was injured throughout the year)

How many players were injured over the year?

In this visualization we will be looking at how many players were injured over the 2021-2022 season. This visualization is interesting because it allows us to see how many players were injured over the year but still remained in the top 300 of fantasy players. What this can show us is that there shouldn’t be many reservations about drafting players that have a tendency to get injured (like Dalvin Cook on the Vikings). Since that player will have performed well enough to have been valuable throughout the season, more so than any other player that you could’ve chosen.

From the visualization we can determine that a significant portion of players in the top 300 had gotten injured and been out for at least one game throughout the season. Looking at the data we can actually see that there were 4 people in the top 10 that had all missed at least one game throughout the year. Although the top 6 were all never hurt, we can reasonably assume that if a player gets hurt, they still have a chance to redeem themselves. Also, there is a player in the top 100 that did get hurt halfway through the season and didn’t come back. So, in sum, avoiding players due to their tendency to get injured is typically not a good strategy.

Is there a correlation between being injured and scoring less points?

Although this may seem like an obvious correlation (you play less games, and score less points), there is another story to be told within this category of being injured in terms of scoring. From the boxplot below we are able to see that there is, indeed, a correlation to not being injured and scoring more points. However, what this plot also tells us is that there were some injured players that scored higher than the average healthy player. What this tells us is that we should be able to feel confident in any injured player that does relatively well at the beginning of the season, and that even if they get hurt we can be be confident that they were a worthy draft pick.

What is the correlation between receiving yards and TD’s per game by position?

What this visualization will show us is which players are better at turning their receiving yards into touchdowns. From the plot below we are able to see that running backs typically have the most efficiency when it comes to turning receiving yards into touchdowns. With that being said, we can typically explain this by thinking logically about where RB’s score the most touchdowns. Passing touchdowns to running backs usually occur within the redzone, while WR’s have more opportunity to score from farther away.

Which position scores the most points per game and which teams are they on?

The reason this question is being asked is to analyze a trend and see whether or not there are teams that typically have players from one specific position score more than players in the same position on different teams. From this box plot, we are able to see that if you are drafting a fantasy team you may want to avoid drafting a NYJ RB over a WAS RB, since WAS RB’s are more likely to score more points per game.

Is there a correlation between fumbles and total points scored by position?

The question I posed is interesting to me in a couple of different ways. I am curious about it because typically players get discouraged or taken out after a fumble unless they are a quarterback. If a player is getting taken out, then that player is typically going to get less points. Also, even if a player stays in, they could get discouraged and have a worse game after the fumble. I believe that these situations could both correlate to less points scored the more fumbles that you get. This hypothesis is supported by the visualization below, as we see those who did not fumble at all scoring more than those that fumbled the ball less often. However, there is some variation to note within each individual positional category. Namely the QB category, as the top 4 highest scoring QB’s all had at least one fumble. This is supporting my note from earlier, that QB’s typically don’t get taken out after they fumble the ball so they still have the opportunity to score more points