A lot of analysis of running vs. passing takes into account the added risk of interceptions. Almost all sources of passing stats will include team or player interceptions. But fumbles are more tricky. Stat sites will tell you team fumbles, but they usually won't tell you how many were due to rushes or due to passes.
Unlike interceptions, fumbles can happen on either type of play. But is the risk of a fumble even between runs and passes, or are fumbles more likely to occur on one or the other type of play? Further, what about fumbles lost? Are fumbles more likely to be lost on runs or passes? And how does the sack-fumble factor in?
Fortunately, with play-by-play data we can tell whether the play was a run or a pass, or if the fumble was lost. And for pass plays, we can also tell whether it was a sack that caused the fumble or whether the receiver dropped the ball after a completion.
Here are the numbers based on all non-preseason games from 2000 through week 10 of 2009. I'm just going to give you a bullet list of the relevant percentages:
- Fumbles occur on 1.67% of all run and pass plays. About half of all fumbles are lost, for an overall rate of 0.83% per play.
- Fumbles occur on 1.16% of run plays. 55% of run play fumbles are lost, for an overall rate of 0.65% per run.
- Fumbles occur on 2.04% of pass plays. 47% of pass play fumbles are lost, for an overall rate of 0.97% per pass play.
- Fumbles occur on 18.0% of all sacks.
- Fumbles occur on 0.96% of all pass completions.
- Of all pass play fumbles, 56% occur due to sacks.
- Sack-fumbles are lost 47% of the time.
- 8.5% of sacks cause a turnover.
- Fumbles after completions are also lost 47% of the time.
And in case anyone is wondering, yes, my recent series of articles on run-pass balance do factor in fumbles. Expected Points Added (EPA) includes anything that can happen on a play--turnovers, sacks, penalties--anything that moves the ball or changes possession.
Hat tip to the Numbers Guy, Carl Bialik for asking the question.