Week 2, Patriots at Bills
4th-and-3, 10:06 remaining in 3rd quarter, Up by 11
The Patriots attempted a field goal on a 4th-and-3 on the Bills’ 3. The NYT 4th Down bot abides, although going for it would have been fine, too.
If you disagree

I lean slightly towards attempting a field goal, but I don’t have strong feelings here – my numbers tell me that either attempting a field goal or going for it could be the best play. Specifically, going for it would be the right call if you think the Patriots’ chances of converting on fourth down are at least 42 percent. (Based on my analysis, I’d give the Patriots a 42 percent chance to get a first down here.)

Here's the full breakdown of my calculations:

Option Chance of converting
Chance of winning
Before play
After play Change
Field goal try20 yard kick (est.) 99% 93% 93% -
Go for it4th and 3, opp. 3 42% 93% 93% -
Punt 93% 88% –5%
My decision in context

Along with some circuitry to come up with a win probability for every game situation, all you need to figure out what you should do next is an estimate of how likely you are to make a field goal or convert a first down.

My estimates for these are based on the results of thousands of similar plays, but you may think you're smarter than I am. This chart shows you how changing those estimates would change my recommendation.

What to do on 4th-and-3 on opp. 3
Up by 11 with 10:06 remaining in the 3rd quarter
What coaches usually do
Field goal try 80% of the time
Go for it 20% of the time
Punt -
Based on about 991 fourth downs in similar situations since 2001.
What happened

Stephen Gostkowski 21 yard field goal attempt is GOOD.

Where did these numbers come from?

To estimate a team’s chances of winning, I use a mathematical model that accounts for a whole lot of variables — including the difference in score, the time remaining in the game, and the number of timeouts each team has left. On top of that, I have models for the likelihood that a team makes a field goal and the likelihood that it will convert a first down.

By combining all of this information, I can come up with the best decision a team can make, according to math.

If you want even more details about the numbers behind my decisions, my full model is available on GitHub. Help make me better!