Welcome back to the second part of this series! I plan for this series to cover one more position, but I can certainly do more if they perform well. In addition, I would like to look at results since 2000 and see if we can find if statistics are becoming more relevant and useful in scouting players. Without further ado, let’s begin!
Today, we are going to look and see what statistics matter the most to scouts in drafting a running back. If these metrics matter when drafting players, they certainly matter to veteran players in terms of how valuable they are. If the results come back that a certain metric is statistically significant, then we can safely assume NFL teams see these statistics as predictors for success in the NFL at their position. For determining if a metric is statistically significant, the p-value needs to be less than .05. If you need to, please reference the first post in this series (“Predicting the NFL Draft with Combine Results – Linear Regression Analysis for Wide Receivers”).
| SUMMARY OUTPUT | ||||
| Regression Statistics | ||||
| Multiple R | 0.568168398 | |||
| R Square | 0.322815329 | |||
| Adjusted R Square | 0.209951217 | |||
| Standard Error | 57.15585293 | |||
| Observations | 15 | |||
| ANOVA | ||||
| df | SS | MS | F | |
| Regression | 2 | 18687.43505 | 9343.717524 | 2.860212369 |
| Residual | 12 | 39201.49828 | 3266.791524 | |
| Total | 14 | 57888.93333 | ||
| Coefficients | Standard Error | t Stat | P-value | |
| Intercept | 2457.017304 | 1351.066541 | 1.818576087 | 0.09400617 |
| 40YD | -385.2460524 | 257.312238 | -1.497192887 | 0.160176751 |
| Speed Score | -5.98132791 | 2.507977114 | -2.384921248 | 0.034452608 |
It turns out that during the 2020 NFL Draft, running backs were more likely to be drafted higher if they had a higher speed score compared to having a better 40 yard dash time. Speed score turns out to be statistically significant in determining when running backs got drafted. On the other hand, 40 yard dash times did not seem to matter that much. These two variables gave us an R Squared (this metric tells us how much of the story these variables tell; 1 being the highest) of .3228 which I found to be quite high. If I were to investigate further, I would look at college quality, rushing yards, receiving yards, touchdowns, and broken tackles. Height and weight turned out to both be statistically insignificant in determining when running backs were drafted.
Please let me know if you would like me to investigate further! Thank you for taking the time to read my article. If you would like, follow me on social media! Links are in the top right hand corner.
-Cody, Founder of Sports Confidant
Sports Confidant Blog: Analytics and Fantasy Sports 