Welcome back to the Data Viz DFS NFL Preview utilizing data science & data visualizations – today our focus is running backs. We will be utilizing rushing yards per game, rushing attempts per game & total TDs to understand what RBs have the best value for week 8. We will also introduce a new statistic – attempts per TD. This will tell us on average – how many attempts it takes a RB to score a TD.
The reason I chose these 3 main statistics is because they all have an r squared score > .5 when compared to fantasy points – which means they have a high positive correlation. You may be saying to yourself “Okay Einstein – what does r squared score or high positive correlation mean & why should I care?” Well luckily for you – I am going to break down correlation, scatter plots, & basic data science principles to give you a more informed choice when picking week 8 RBs. Basically I’m going to use nerdy math shit to win you money & win the week. Keep reading for a full breakdown & analysis, but only if you like winning.
Today’s first viz is 3 different scatter plots – with each being compared to total fantasy points (y axis). The three statistics on the x-axis are: total TDs, rushing yards per game, & rushing attempts per game. Each circle represents a different RB, the color is based on total fantasy points (blue is good & orange is bad), & all are positively correlated based on their r squared score (>.5).
Before we jump head first into the analysis, let’s define a few key terms.
Key Terms:
Scatter Plot: A graph where the values of two variables are plotted along two axes (x & y), the pattern of the resulting points reveal if any correlation is present. The purpose of a scatter plot is to show possible associations or relationships between two variables.
Correlation: The process of establishing a relationship or connection between two or more variables.
Positive Correlation: The values of one variable increase as the values of the other increase. Basically if you improve one variable – you will see improvement in the other.
R Squared Score / Correlation Score: The main purpose is to predict future outcomes on the basis of other related information. In general the higher the R-squared score, the more confident you can be when predicting future outcomes.
Key Takeaways:
Takeaway #1: Total TDs & rushing yards per game make up the fantasy equation for RBs – so obviously these two statistics are going to correlate heavily with total fantasy points. Total TDs has a .75 r squared score & rushing yards per game has a .71 r squared score. We will utilize these 2 stats as staples when predicting future performance due to their high correlation score.
Takeaway #2: Rushing attempts per game has just as high an r squared score as the 2 previously mentioned statistics (total TDs & rushing yds per game). Basically the more rushing attempts a RB receives – the more likely the RB will put up rushing yards which leads directly to fantasy points. Again, nothing earth shattering here yet. But due to how high this r squared score is we feel very confident utilizing this to predict future performance.
Takeaway #3: If rushing attempts per game leads directly to rushing yards per game – is there a similar statistic we can utilize that leads directly to TDs? This is where the statistic – attempts per TD comes into play. This is my attempt at creating a new statistic to see if we can understand how many rushing attempts it takes the RB to score, on average. Then take that number and forecast for the next week.
Takeaway #4: Continue reading as I present a visual with these stats plus receiving targets per game. I will also present players I like & don’t like for week 8 below, but remember this is just my opinion based on the data & my gut feel. There are many correct answers when it comes to predicting daily fantasy football, so do your own research & always make your own picks based on how comfortable you feel with the player. Hopefully this gives you a great starting point & a general direction to follow when researching for the week.
This viz is a lollipop chart where the length of the lollipop shows atttempts per TD (the lower the attempts the better), the width of the circle represents total receiving targets, & the color of the lollipop represents rushing yards per attempt (blue is good & orange is bad). The RBs are ordered by DK fantasy points per game (left to right). Continue reading for the RBs I like & don’t like for week 8.
Top 20 RBs
RBs I Like For Week 8
Aaron Jones vs Chiefs | Leonard Fournette vs Jets | Phillip Lindsay vs Colts| James Conner vs Dolphins | Devonta Freeman vs Seahawks | Todd Gurley vs Bengals
RBs I Do Not Like For Week 8
Christian McCaffrey vs 49ers | Nick Chubb vs Patriots | Derrick Henry vs Bucs | Le’Veon Bell vs Jaguars | Royce Freeman vs Colts
21 – 40 RBs
RBs I Like For Week 8
Chase Edmonds vs Saints | Marlon Mack vs Broncos | LeSean McCoy vs Packers| Saquon Barkley vs Lions | David Montgomery vs Chargers
RBs I Do Not Like For Week 8
Jordan Howard vs Bills | Carlos Hyde vs Raiders | Joe Mixon vs Rams | Rex Burkhead vs Browns
41 – 60 RBs
Ask me any questions about Data, Visuals, DFS, etc. on Twitter (@StephenDataViz) or Instagram (@StephenDataViz)
