Take You Out, Coach: Why NFL Coaches Get Sacked

Introduction

While I am continuing to gather more data for predicting NFL game outcomes, I am exploring the data I gather for insights and interesting facts.  My most recent exploration comes from looking at yearly team data with the coach included for each year.  From that I can determine how long a coach has been on that same team, if there was a coaching change, and what impact a coaching change has.  I can also gain some insight as to why a coach is fired.  Here are some things I discovered.

Random Facts about Coaches

• Most years coaching for a single team in a row?
• 29 years by Landry of the Dallas Cowboys, 1960 -1988 and Lambeau for the Packers 1921-1949.  Others: Shula (26, Dolphins), Owen (23, Giants), and Noll (23, Steelers)
• Current coaches: Belichick (16, Patriots), Lewis (13, Bengals), and Coughlin (12, Giants)
• Most years coaching for a single team:
• 39 years for Halas for the Bears.  From 1920-1929, 1933-1941, 1946-1955,1958-1967
• Average years of coaching for a single team: 4 years (median of 3)







• Most coaches only get 2 years, but 1 year is closely behind
• Most wins: Shula (346), Halas (313), Landry (250)
• Most losses: Shula (202), Landry (162), Reeves (155)
• Highest overall win ratio by a retired coach over more than a single season: Madden (.72)
• Current coach over more than one season: Arians (.70), McCarthy(.68), and Belichick (.67)
• Most teams coached for (depends on how you count it, but...):
•  Phillips (5), Edwards, Johnson, Mora, Parcells, Ryan, Saban, Schottenheimer, Turner (4)
• Most playoff appearances:
• Shula (19), Landry (18), Brown (15), Belichick (13), Schottenheimer (13)
• Most years since playoffs with the same coach:
• Halas (8), Lambeau (7), Parker (7), Wilson (7), Starr (6)
• Most years since playoffs by any team:
• The Cardinals were out of the playoffs for 25 years straight from 1949-1973.  The Redskins were also out for 25 years from 1946-1970.
• Current: Bills (16), Browns (13), and Raiders (13)

Coaching Changes and Win Ratio

Does a coaching change make a difference in the following year?  If we look at the Win Ratio (wins/(wins+losses+ties)), the win ratio in years where there is no coach change (i.e., the same coach as previous year) is higher on average than years where there is a coach change (i.e., a different coach from previous year).  No coach change years have an average win ratio of .53 while coach change years have an average of .40.  The graph of the distribution is below.

But perhaps it is lower because the previous coach was doing such a poor job, and so the new coach has a bad team to start with and needs time to rebuild.  We can compare the win ratio of coaches on their last year with those in their first year (i.e., a coach change), and we find out that they are virtually the same.  Coaches in their last year have a slightly lower win ratio (.38), but the distribution looks basically the same:

In fact, if we look at coaches who are not in their first year or in their last year, these coaches have an average win ratio of .57.  The distribution is below:

So what we might expect is that a coach will do fairly poorly his first year as he rebuilds a broken team, he will do better in his middle years, but as his win ratio declines, he is headed for his last year as a coach for the particular team.  That is, after a grace period, a coach's continued employment depends on the win ratio.  This seems reasonable.  But here is what that journey looks like, plotting the win ratio for every coach/team combo over the duration of that coach's time with the team (duration is calculated by year of coaching for the team divided by total years of coaching for the team):

There is no pattern here.  In fact, win ratio appears to have nothing to do with a coach's duration.  But perhaps the average win ratio for each duration follows the pattern we would expect.  In fact, there is a broad trend of rising and then falling of the average win ratio through the tenure of all coaches as a group:

However, for any given individual coach, this trend may not be followed perfectly.  Here are some examples:

Some coaches finish their last year coaching with a decent win ratio, and as we have seen there is a lot of variation.  So while it is an important part of the reason why a coach may be let go, it is not the only reason. 

Why Do Coaches Get Fired (or Retire or ...)

Most coaches do not get fired (or retire) each year.  Over the history of the NFL, a coach has been in his last continuous year of coaching for the same team about 27% of all year/team/coach combinations.  If trying to predict if a coach will be coaching his last year, one could simply predict for all year/team/coach combinations that he will not be coaching his last year, and one would be correct 73% of the time.  Obviously, this is not helpful if we are trying to predict when a coach will be fired/retired, since all of these predictions will be wrong.  So the success of model in this instance is how well it predicts the firing/retiring of a coach specifically.

Coaches are likely fired/retired for many reasons not directly observable to the public: administrative conflicts, new opportunities, actual retirement, family reasons...  Such things are not readily known and as a result cannot be included in a model.  What is known (and what I will be focusing on) is each coach's football stats with his team prior to his firing/retiring.  In particular:

• Wins, Losses, Ties, Win Ratio Previous years win ratio comparison
• Made Playoffs that year, Years since playoffs with that coach
• Team ranks (offensive, defensive, overall)
• Years Coaching

These factors are easily measurable, publicly measurable, and intuitively important in whether a coach is fired/retired.  According to my models, here are the important factors and some comments on them:

• Win Ratio:
• Having a 0.50+ win ratio strongly indicates that the coach will NOT be fired/retired, although it is not perfect.
• Point Difference (points for - points against)
• A negative point difference likely means the coach will be fired/retired, unless he has better than average points for.  If that is the case, then what seems to matter is the current win ratio compared to previous years. 
• If the coach does not have better than average points for and has a negative point difference, the coach will likely be fired/retired.
• Win Ratio Differences
• If  there has been a 30% drop in win ratio over the past three years, then the coach will most likely be fired/retired.
• If not,  and the coach has appeared to have peaked already in win ratio, then its a toss up whether the coach will keep his job or not.
• Drops in win ratio from two years prior and also the previous year indicate the coach is likely to be fired/retired.
• Wins
• Having more than 10 wins suggests the coach will NOT be fired/retired, although it is not perfect.
• Years Coaching
• If a coach has a win ratio less than 0.50, and has only coached one year, he is more likely to be fired/retired than not, but only slightly.  Surviving at least two years greatly improves his changes of not being fired.  In fact, the more years you coach, the less likely you are to be fired/retired.
• Offensive Rank
• With a losing record in the season, a coach can still keep his job if his team's offensive rank by points is in the top 6 (i.e., 1-6).  In one model, each decrease (e.g., 7 to 8) in offensive rank increased the coach's chances of firing by 3%.
• Years Since Playoffs with Same Coach
• In some models, this really mattered.  In one, for every year not going to the playoffs, the coach's chances of being fired/retired increased by about 15%.  The longer the coach is out of the playoffs with his team, the more likely he will be fired.
• Although a bit unfair, a team's being out of the playoffs for a long time increases a coach's chances of being fired, even when that coach was not responsible for the long drought that preceded him.

In summary, a coach will likely be fired/retired if some combination of the following factors is present in any given year: a win ratio of less than 50%, a declining win ratio from previous years, a low scoring offense, more points against than for, fewer years coaching for the team, and several years since a playoff appearance.

Who Has to Worry in 2015?

Based on the above considerations and modeling, who should be most worried in 2015 with the way things are at present?  I would have said Philbin of the Dolphins, but he already got fired.  After him, I believe Payton and Tomsula have the most to be worried about:

• Payton (Saints)
• The Saints had a bad year last year and this year doesn't look any better, although the recent win against the Falcons may bring hope.  Nevertheless, the best seems to be in the past for Payton, at least as far as his time with the Saints is concerned.  I rate him as 75% likely to be fired/retired.
• Tomsula (49ers)
• The 49ers are off to a really bad start.  They didn't make the playoffs last year, and this year is not looking good either.  While it is Tomsula's first year, that may make it harder to keep his job if he can't turn things around soon.  I rate him as 75% likely to be fired/retired.

Others that may have reason to worry: Harbaugh (Ravens), Garrett (Cowboys), Caldwell (Lions), and McCoy (Chargers).

Conclusion

 It is not surprising that coaches are largely fired because they have started losing and are not going to the playoffs.  What is slightly surprising is that the longer a coach is coaching, the more likely he is to continue coaching.  I suppose that past success can help sustain a coach into the future, at least for a while.  Also a bit surprising initially but not after reflection, is the fact that, even though the team has a losing record, as long as the team is putting up lots of points, the coach will likely be retained.  After all, what do fans want to see?  Wins, playoffs, and lots of points being scored by their team.  A great defense is necessary to win championships, but it is not as glamourous or as fun to watch as a great offense.

Good luck in week 6!