Off The Chain

Husband and father. Creator of Tastevin. Former winemaker. Stats nerd.

Read this first

Why Expected Points and EPA are kind of broken

tl;dr EPA is difficult to calculate, hard to explain, is inherently noisy, and isn’t more stable than metrics like fantasy points that are far easier to understand and calculate.

Why EPA should be awesome

When it was introduced by Brian Burke by way of Virgil Green, EPA (Expected Points Added) promised to be a breakthrough in NFL player evaluation. EPA accounts for down, distance remaining to gain a first down, and field position. It also accounts for garbage time. Therefore we might expect EPA to better measure true skill in NFL players. This is exciting. Metrics with this type of potential are pretty rare.

How to calculate EPA (it’s hard)

EPA is calculated by taking the expected point value of every down, distance and field position (“game state”) combination before a play is run, and subtracting it from the expected point value of the new game state after a play is run...

Continue reading →

Tracking My Predictions

There is very little incentive to track your own predictions in Fantasy Football. It’s entertainment first and foremost, and looking back and seeing that you were wrong is the opposite of fun. Moreover, there is no real downside to being wrong - most people don’t care enough to track an analyst’s failures and then hold it against them. And analysts seldom hold other analysts accountable since that would mean opening themselves up to the same scrutiny.

Still, you can’t measure what you don’t track, and what you don’t measure you can’t improve. So here are my 2016 FF predictions. Note that BUY simply means I see a >= 75% chance that a player will outperform his ADP, and a SELL means I see a >= 75% chance that a player will underperform his ADP.

  • Matt Jones is a BUY at RB 21. - Rotoviz, published 5/20/16
  • Rashad Jennings is a BUY at RB 42 - Rotoviz, published 5/31/16
  • Kamar Aiken is a...

Continue reading →

Projecting Running Backs using Age Adjusted Correlation Curves and Historical Comps

tl;dr Fantasy players who draft based on efficiency will be consistent league losers. A player’s per game production in year Y correlates to Y+1 production to varying degrees depending on the player’s age. During a player’s prime years, which are longer than many might expect, the correlation is exceptionally strong. Combining these production coefficients with historical comps can provide for better pre-season projections for NFL Running Backs

There are a couple universal truths in fantasy football, and they are directly related.

The first is that if you can accurately project volume (and its sexy and mysterious friend opportunity), you will probably win your league. Nothing correlates to fantasy points like volume of touches.

The second is that efficiency metrics are complete garbage when the goal is to try and predict what will happen in the future. Yards per carry (YPC) is...

Continue reading →

Introducing SPORK

tl;dr Here are the coefficients to calculate SPORK, a close approximation of pSPARQ (r2 .959), which itself is an approximation of SPARQ.

It’s turtles all the way down.

(Intercept) 181.924227
HT           -4.592111
WT            0.361056
X40         -15.159259
X10         -45.532307
Shuttle     -18.731278
X3Cone       -5.985102
Bench         0.252199
Vert          1.327290
Broad         9.557272

Here is a link to a Google doc applying the formula.

Sports analytics nerds are a funny lot. We obsess over things like mean squared errors and trying find year over year correlations for the beard growth on Julian Edleman. Our curiosity drives us to do strange things in the pursuit of knowledge.

It has always been this way. Hackers with the same drive reverse engineered arcade machines and built emulators so they could play Dig Dug on their home computer. Then they posted the source...

Continue reading →