## Defensive Fumbles Forced

If fumble recoveries are random, should defenses be credited with fumbles or fumble recoveries that result from unforced fumbles? How would a defense induce an unforced fumble, such as a muffed snap or handoff? I'm guessing it can't.

So if unforced fumbles are not under the influence of a defense, and if recoveries are random, then a defense's ability to produce fumble turnovers should be measured by forced fumbles no matter who recovers them. And to be more precise, the best measure would be forced fumbles per play (in which a forced fumble is plausible, i.e. not incomplete passes).

If this is true, the win- and points- correlations with forced fumble (FF) rate will be higher than gross FFs, fumbles, or fumble recoveries. I would expect that fumble takeaways might still have the strongest correlations, but because recoveries are random, I believe that it does not estimate future fumbles as well as forced fumbles.

Here are the correlations:

As it turns out, I was partially correct, but the forced fumble rate statistic turns out to be more powerful than anticipated. Not only does defensive forced fumbles have stronger correlations to wins and points than gross fumbles and fumbles recovered, the defensive forced fumble rate stat (FF per fumble-potential play) has the strongest correlation of all (0.41).

In summary, the data suggests I use 'defensive forced fumble rate' as the defensive fumble stat for a win-regression model. It also suggests (noted in previous posts) that I use offensive fumbles, and not offensive fumbles lost. These stats correlate relatively strongly with winning, points scored, and points allowed; they do not suffer from the random noise of fumble recovery; and, since they are 'per play' rate stats, they are not biased by the causation backflow discussed in the interception post.

### 4 Responses to “Defensive Fumbles Forced”

1. jworkm05 says:

Can you explain to me why you have omitted incomplete passes from consideration with regard to forced fumbles.....it seems to met that there still exists the opportunity for the defense to force a fumble in the way of a sack. How are we to know whether the pass that would have been thrown by a qb who is sacked and fumbles would have been complete or incomplete???

2. Brian Burke says:

jworkm-
Excellent point. At first I didn't understand what you were saying, but now it's clear. It would probably be best to account for the fact a sack did not occur on an incomplete pass.

What I was originally trying to do was evaluate a defense's ability to force a fumble during a tackle. Since there is never tackle on an incomplete pass, there would be no possibility of forcing a fumble.

But you're right, a defense that gets a lot of sacks also probably forces a lot of fumbles by the QB. In the context of assessing a team's ability to generate fumbles, sack rates would be critical.

In fact, I'd bet sack rates are one of the best predictors of future forced fumbles--even better than previous forced fumbles to date.

Thanks.

3. Brian Burke says:

I just looked at some numbers. Actually, it appears that prior fumble rates predict future fumble rates (within the same season) at a 0.33 correlation. Sack rates predict fumble rates at only 0.15, which is pretty small and barely significant. I'm sure it would be higher for forced fumbles, but I don't have mid-season forced fumble data to check.

Regardless, I think you're point is correct.

4. Justin says:

I'm working on a project that needs to incorporate fumbles as a measure of rush defense and I've arrived at conclusions similar to yours. The best measure would be fumbles truly forced by the defense, regardless of who recovers. But like I said, I'm looking at this as a measure of rush defense, so I want to exclude fumbles produced on sacks, as they're clearly a component of pass defense. Do you have a source for fumble stats that could provide detail at this level?