Home field advantage is naturally higher in a hitter's park

The Rockies have always had a huge home-field advantage (HFA) at Coors. From 1993 to 2001, Colorado has played .545 at home, but only .395 on the road. That's the equivalent of the difference between going 89-73 and 64-98. 

Why such a big difference? I have some ideas I'm working on, but the most obvious one -- although it's not that big, as we will see -- is that higher scoring naturally, mathematically, leads to a bigger HFA.

When teams play better at home than on the road -- for whatever reason --the manifestation of "better" is in physical performance, not winning percentage as such. The translation from performance to winning percentage depends on the characteristics of the game. 

In MLB, historically, the home team plays around .540. But if the commissioner decreed that now games were going to be 36 innings long instead of 9, the home advantage would roughly double, with the home team now winning at a .580 pace.

(Why? With the game four times as long, the SD of the score difference by luck would double. But the home team's run advantage would quadruple. So the run differential by talent would double compared to luck. Since the normal distribution is almost linear at such small differences (roughly, from 0.1 SD to 0.2 SD), HFA would approximately double.)

But it's not *always* that a higher score number increases HFA. If it was decided that all runs now count as 2 points, like in basketball, scoring would double, but, obviously, HFA would stay the same. 

Roughly speaking, increased scoring increases the home advantage only if it also increases the "signal to noise ratio" of performance to luck. Increasing the length of the game does that; doubling all the scores does not.

In 2000, Coors Field increased scoring by about 40%. If that forty percent was obtained by increasing games from 9 innings to 13 innings, HFA would be around 20% higher. If the forty percent was obtained by making every run count as 1.4 runs, HFA would be 0% higher. In reality, the increase could be anywhere  between 0% and 20%, or beyond.

We probably have the tools available to get a pretty good estimate of the true increase.

------

Let's start with the overall average HFA. My subscription to Baseball Reference allowed me to obtain home and road batting records, all teams combined, for the 1980-2022 seasons:

         AB        H     2B    3B    HR     BB     SO
------------------------------------------------------
home   3209469 846723 161290 19928 95790 321178 612545
road   3363640 859813 163954 17203 96043 308047 668363

What's the run differential between those two batting lines? We can look at actual runs, or even the difference in run statistics like Runs Created or Extrapolated Runs. But, for better accuracy, I used Tom Tango's on-line Markov Calculator (the version modified by Bill Skelton, found here). It turns out the home batting line leads to 4.79 runs per nine innings, and the road batting line works out to 4.36 R/9.

         AB        H     2B    3B    HR     BB     SO    R/9
-------------------------------------------------------------
home   3209469 846723 161290 19928 95790 321178 612545  4.79
road   3363640 859813 163954 17203 96043 308047 668363  4.36
-------------------------------------------------------------
difference                                              0.43

That's a difference of 0.43 runs per game. Using the rule of thumb that 10 runs equals one win, a rough estimate is that the home team should have a win advantage of 0.043 wins per game, for a winning percentage of .543. 

That's a pretty good estimate -- home teams actually went .539 in that span (51832-44409). But, we'll actually need to be more accurate than that, because the "10 runs per win" figure will change significantly for higher-scoring environments such as Coors. 

So let's calculate an estimate of the actual runs per win for this scoring environment.

The Tango/Skelton Markov calculator includes a feature where, given the batting line, it will show the probability of a team scoring any particular number of runs in a nine-inning game. Here's part of that output:

          home   road
----------------------
2 runs:  .1201  .1342
3 runs:  .1315  .1404
4 runs:  .1282  .1309

From this table, which actually extends from 0 to 30+ runs, we can calculate how many runs it would take for the road team to turn a loss into a win.

Case 1:  If the road team is tied after 9 innings, it has about a 50% chance of winning. With one additional run, it turns that into 100%. So an additional run in a tie game is worth half a win.

How often is the game tied? Well, the chance of a 2-2 tie is .1202*.1342, or about 1.6%. The chance of a 3-3 tie is .1315*.1404, or 1.8%. Adding up the 2-2 and the 3-3 and the 0-0 and the 1-1 and the 4-4 and the 5-5, and so on all the way down the line, the overall chance is 9.7%.
 
Case 2:  If the road team is down a run after 9 innings, it loses, which is a 0% chance of winning. With one additional run, it's tied, and turns that into a 50% chance. So, an additional run there is also worth half a win.

How often is the road team down a run? Well, the chance of a 3-2 result is .1315*.1342, or about 1.8%. The chance of 4-3 is .1282*.1404, another 1.8%. And so on.

The total: a 9.54% chance the road team winds up losing by one run.

What's the chance that the additional run will give the *home* team the extra half win? We can repeat the calculation, but instead of 3-2, we'll calculate 2-3. Instead of 4-3, we'll calculate 3-4. And so on.

The total: only 8.54%. It makes sense that it's smaller, because the better team is less likely to be behind by a run than ahead by a run.

We'll average the home and road numbers to get 9.04%. 

So, we have:

9.7% chance of a tie
9.0% chance of behind one run
----------------------------------------------
18.7% chance that a run will create half a win

Converting that 18.7% chance to R/W:

    0.187 half-wins per run  
=   5.35 runs per half-win 
=   10.7 runs per win

So, we'll use 10.7 runs per win for our calculation.

(Why, by the way, do we get 10.7 runs per win instead of the rule of thumb that it should be 10.0 flat? I think it's becuase the Markov simulation always plays the bottom of the ninth, even when the home team is already up. It therefore includes a bunch of meaningless runs that don't occur in reality. When some of the run currency is randomly useless, it pushes the price of a win higher.

We'd expect that roughly 1/18 of all runs scored are in the bottom of the ninth with the home team having already won. If we discount those by multiplying 10.7 by 17/18, we get ... 10.1 runs per win. Bingo.)

We saw earlier that the home team had an advantage of 0.43 runs per game. Dividing that by 10.3 runs per win, gives us

Predicted: HFA of .42 wins per game (.542)
Actual:    HFA of .39 wins per game (.539)

We're off a bit. The difference is about 2 SD. My guess is that the Markov calculation, which is necessarily simplified, is very slightly off, and we only notice because of the huge sample size of almost 100,000 actual games. 

-------

OK, now let's do the same thing, but this time for Coors Field only.

I could do the same thing I did for MLB as a whole: split the combined Coors batting line into home and road, and calculate those individually. The problem with that is ... well, if I do that, I'll be getting the Rockies' actual HFA at Coors, which is huge, because it includes all kinds of factors that we're not concerned with, like altitude acclimatization, tailoring of personnel to field, etc.

So, I'm going to try to convert the Coors line into an approximation of what the split would look like if it were similar to MLB as a whole.

Here's that 1980-2022 MLB split from above, except I've added the percentage difference between home and road (on a per-AB basis) below:

         AB        H     2B      3B     HR     BB     SO
---------------------------------------------------------
home   3209469 846723 161290   19928  95790 321178 612545
road   3363640 859813 163954   17203  96043 308047 668363
---------------------------------------------------------
diff            +3.2%  +3.5%  +21.4%  +4.5%  +9.3%  -3.9%

I'll try to create something similar for 2000 Coors.  The overall batting line, for both teams, looked like this:

         AB    H   2B 3B  HR  BB  SO     R/9   
---------------------------------------------
Coors  5843  1860 359 56 245 633 933    7.43

Here's my arbitrary split, into Rockies vs. road team, in such a way to keep roughly the same percentage differences as in MLB overall, while also keeping the R/9 roughly 7.43. Here's what I came up with:
     

          AB      H      2B     3B      HR     BB     SO  
--------------------------------------------------------
  home   5843   1884    362     66     249    672    936
  road   5843   1826    350     54     238    615    974
--------------------------------------------------------
  diff         +3.2%  +3.4%  +22.2%  +4.6%  +9.3%  -3.9%

I ran those through Tango's calculator to get runs per 9 innings:

          AB     H    2B     3B   HR    BB    SO     R/9
---------------------------------------------------------
  home   5843  1884  362     66  249   672   936    7.783
  road   5843  1826  350     54  238   615   974    7.071
---------------------------------------------------------
  avg                                               7.427
---------------------------------------------------------
  diff                                              +.712

Next, I ran the runs-per-game distribution calculation to get a runs-per-win estimate. (I won't go through the details here, but it's the same thing as before: calculate the probability of a tie, then a one-run home win, then a one-run road win, etc.)

The result: 14.37 runs per win. 

As expected, that's significantly higher than the 10.7 we calculated for MLB overall. (Adjusting 14.37 for the superfluous bottom-of-the-ninth gives about 13.6, so, if you prefer, you can compare 13.6 Coors to 10.1 overall.)

The difference of .712 runs per game, divided by 14.43 runs per win, gives an HFA of 

0.0495 wins per game

Which translates to a home winning percentage of .5495. 

Comparing the two results:

.542 home field winning percentage normal
.549 home field winning percentage Coors
-----------------------------------------
.007 difference

The difference of .007 is worth only about half a win per home season. Sure, half a win is half a win, but I'm a little disappointed that's all we wind up with after all this work. 

It's certainly not as much of an effect as I thought there would be before I started. Even if you deducted this inherent .007, it would barely make a dent in the Rockies' 150 percentage point difference between Coors and road. The Rockies would still be in first place on the FanGraphs chart by a sizeable margin -- 42 points instead of 49.

Looked at another way, an additional .007 would move an average team from the middle of the 29-year standings, to about halfway to the top. So maybe it's not that small after all.

Still, our conclusion has to be that the Rockies' huge HFA over the years is maybe 10 percent a mathematical inevitability of all those extra runs, and 90 percent other causes.

Why the 2016 AL was harder to predict than the 2016 NL

In 2016, team forecasts for the National League turned out more accurate than they had any right to be, with FiveThirtyEight's predictions coming in with a standard error (SD) of only 4.5 wins. The forecasts for the American League, however, weren't nearly as accurate ... FiveThirtyEight came in at 8.9, and Bovada at 8.8. 

That isn't all that great. You could have hit 11.1 just by predicting each team to duplicate their 2015 record. And, 11 wins is about what you'd get most years if you just forecasted every team at 81-81.

Which is kind of what the forecasters did! Well, not every team at 81-81 exactly, but every team *close* to 81-81. If you look at FiveThirtyEight's actual predictions, you'll see that they had a standard deviation of only 3.4 wins. No team was predicted to win or lose more than 87 games.

Generally, team talent has an SD of around 9 wins. If you were a perfect evaluator of talent, your forecasts would also have an SD of 9. If, however, you acknowledge that there are things that you don't know (and many that can't be known, like injuries and suspensions), you'll forecast with an SD somewhat less than 9 -- maybe 6 or 7.

But, 3.4? That seems way too narrow. 

Why so narrow? I think it was because, last year, the AL standings were themselves exceptionally narrow. In 2015, no American League team won or lost more than 95 games. Only three teams were at 89 or more. 

The SD of team wins in the 2015 AL was 7.2. That's much lower than the usual figure of around 11. In fact, 7.2 is the lowest for either league since 1961. In fact, I checked, and it's the lowest for any league in baseball history! (Second narrowest: the 1974 American League, at 7.3.)

Why were the standings so compressed? There are three possibilities:

1. The talent was compressed;

2. There was less luck than normal;

3. The bad teams had good luck and the good teams had bad luck, moving both sets closer to .500.

I don't think it was #1. In 2016, the SD of standings wins was back near normal, at 10.2. The year before, 2014, it was 9.6. It doesn't really make sense that team talent regressed so far to the mean between 2014 and 2015, and then suddenly jumped back to normal in 2016. (I could be wrong -- if you can find trades and signings those years that showed good teams got significantly worse in 2015 and then significantly better in 2016, that would change my mind.)

And I don't think it was #2, based on Pythagorean luck. The SD of the discrepancy in "first-order wins" was 4.3, which larger than the usual 4.0. 

So, that leaves #3 -- and I think that's what it was. In the 2015 AL, the correlation between first-order-wins and Pythagorean luck was -0.54 instead of the expected 0.00. So, yes, the good teams had bad luck and the bad teams had good luck. (The NL figure was -0.16.)

-------

When that happens, that luck compresses the standings, it definitely makes forecasting harder. Because, there's not as much information on how teams differ. To see that, consider the extreme case. If, by some weird fluke, every team wound up 81-81, how would you know which teams were talented but unlucky, and which were less skilled but lucky? You wouldn't, and so you wouldn't know what to expect next season.

Of course, that's only a problem if there *is* a wide spread of talent, one that got overcompressed by luck. If the spread of talent actually *is* narrow, then forecasting works OK. 

That's what many forecasting methods assume, that if the standings are narrow, the talent must be narrow. If you do the usual "just take the standings and regress to the mean" operation, you'll wind up implicitly assuming that the spread of talent shrank at the same time as the spread in the standings shrank.

Which is fine, if that's what you think happened ... but, do you really think that's plausible? The AL talent distribution was pretty close to average in 2014. It makes more sense to me to guess that the difference between 2014 and 2015 was luck, not wholesale changes in personnel that made the bad teams better and the good teams worse.

Of course, I have the benefit of hindsight, knowing that the AL standings returned to near-normal in 2016 (with an SD of 10.2). But it's happened before -- the record-low 7.3 figure for the 1974 AL jumped back to an above-average 11.9 in 1975.

I'd think when I was forecasting the 2016 standings, I might want to make an effort to figure out which teams were lucky and which ones weren't, in order to be able to forecast a more realistic talent SD than 3.5 wins.

Besides, you have more than the raw standings. If you adjust for Pythagoras, the SD jumps from 7.2 to 8.6. And, according to Baseball Prospectus, when you additionally adjust for cluster luck, the SD rises to 9.4. (As I wrote in the P.S. to the last post, I'm not confident in that number, but never mind for now.)

An SD of 9.4 is still smaller than 11, but it should be workable.

Anyway, my gut says that you should be able to differentiate the good teams from the bad with a spread higher than 3.4 games ... but I could be wrong. Especially since Bovada's spread was even smaller, at 3.3.

-------

It's a bad idea to second-guess the bookies, but let's proceed anyway.

Suppose you thought that the standings compression of 2015 was a luck anomaly, and the distribution of talent for 2016 should still be as wide as ever. So, you took FiveThirtyEight's projections, and you expanded them, by regressing them away from the mean, by a factor of 1.5. Since FiveThirtyEight predicted the Red Sox at four games above .500 (85-77), you bump that up to six games (87-75).

If you did that, the SD of your actual predictions is now a more reasonable 5.1. And those predictions, it turns out, would have been better. The accuracy of your new predictions would have been an SD of 8.4. You would have beat FiveThirtyEight and Bovada.

If that's too complicated, try this. If you had tried to take advantage of Bovada's compressed projections by betting the "over" on their top seven teams, and the "under" on their bottom seven teams, you would have gone 9-5 on those bets.

Now, I'm not going to so far as to say this is a workable strategy ... bookmakers are very, very good at what they do. Maybe that strategy just turned out to be lucky. But it's something I noticed, and something to think about.

-------

If compressed standings make predicting more difficult, then a larger spread in the standings should make it easier.

Remember how the 2016 NL predictions were much more accurate than expected, with an SD of 4.5 (FiveThirtyEight) and 5.5 (Bovada)? As it turns out, last year, the SD of the 2015 NL standings was higher than normal, at 12.65 wins. That's the highest of the past three years:

2014  AL= 9.59, NL= 9.20
2015  AL= 6.98, NL=12.65
2016  AL=10.15, NL=10.71

It's not historically high, though. I looked at 1961 to 2011 ... if the 2015 NL were included, it would be well above average, but only 70th percentile.*

(* If you care: of the 10 most extreme of the 102 league-seasons in that timespan, most were expansion years, or years following expansion. But the 2001, 2002, and 2003 AL made the list, with SDs of 15.9, 17.1, and 15.8, respectively. The 1962 National League was the most extreme, at 20.1, and the 2002 AL was second.)

A high SD won't necessarily make your predictions beat the speed of light, and a low SD won't necessarily make them awful. But both contribute. As an analogy: just because you're at home doesn't mean you're going to pitch a no-hitter. But if you *do* pitch a no-hitter, odds are, you had the help of home-field advantage.

So, given how accurate the 2016 NL forecasts were, I'm not surprised that the SD of the 2015 NL standings was higher than normal.

-------

Can we quantify how much compressed standings hurt next year's forecasts? I was curious, so I ran a little simulation. 

First, I gave every team a random 2015 talent, so that the SD of team talent came out between 8.9 and 9.1 games. Then, I ran a simulated 2015 season. (I ran each team with 162 independent games, instead of having them play each other, so the results aren't perfect.)

Then, I regressed each team's 2015 record to the mean, to get an estimate of their talent. I assumed that I "knew" that the SD of talent was around 9, so I "unregressed" each regressed estimate away from the mean by the exact amount that gets the SD of talent to exactly 9.00. That became the official forecast for 2016. 

Finally, I ran a simulation of 2016 (with team talent being the same as 2015). I compared the actual to the forecast, and calculated the SD of the forecast errors.

The results came out, I think, very reasonable.

Over 4,000 simulated seasons, the average accuracy was an SD of 7.9. But, the higher the SD of last year's standings, the better the accuracy:

SD Standings    SD next year's forecast
------------------------------------
7.0             8.48 (2015 AL)
8.0             8.31
9.0             8.14
10.0            7.98
11.0            7.81
12.0            7.64
12.6            7.54 (2015 NL)
13.0            7.47
14.0            7.31
20.1            6.29 (1962 NL)

So, by this reckoning, you'd expect the 2016 NL predictions to have been one win more accurate than than the AL predictions. 

They were "much more accurater" than that, of course, by 3.4 or 4.5. The main reason, of course, is that there's a lot of luck involved. Less importantly, this simulation is very rough. The model is oversimplified, and there's no assurance that the relationship is actually linear. (In fact, the relationship *can't* be linear, since the "speed of light" limit is 6.4, and the model says the 1974 AL would beat that, at 6.3). 

It's just a very rough regression to get a very rough estimate. 

But the results seem reasonable to me. In 2016, we had (a) the narrowest standings in baseball history in the 2015 AL, and (b) a wider-than-average, 70th percentile spread in the 2016 NL. In that light, an expected difference of 1 win, in terms of forecasting accuracy, seems very plausible. 

--------

So that's my explanation of why this year's NL forecasts were so accurate, while this year's AL forecasts were mediocre. A large dose of luck -- assisted by a small (but significant) dose of extra information content in the standings.

National League forecasts were too accurate in 2016

FiveThirtyEight predicted the National League surprisingly accurately this year.

The standard error of their predictions -- that is, the SD of the difference between their team forecasts, and what actually happened -- was only 4.5 games.* (Here's the link to their forecast -- go to the bottom and choose "April 2".)

(* The SD is the square root of the average squared error. If you prefer just the average error, in this case, it was three-and-a-third games. But I'll be using just the SD in the rest of this post. In most cases, to estimate average error when you only have the SD, you can multiply by 2/pi (approximately 0.64).)

4.5 games is very, very good. In fact, it's so good it can't possibly be all skill. The "speed of light" limit on forecasting MLB is about 6.4 games. That is, even if you knew absolutely everything about the talent of a team and its opposition, every game, an SD of 6.4 is the very best you could expect to do.

Of course, you can get lucky, and beat 6.4 games. You could even get to zero, if fortune smiles on you and every team hits your projection exactly. But, 6.4 is the best you can do by skill.**  

(** Actually, it might be a bit less, 6.3 or something, because 6.4 is what you get when teams are evenly matched ... mismatches are somewhat easier to predict. But never mind.)

How unusual is an SD of 4.5? Well, not *that* unusual. By my estimate, the SD of the observed SD -- sorry if that's a little confusing -- is somewhere around 1.7, for a league of 15 teams. So, FiveThirtyEight was a little over one standard deviation lucky, which isn't really a big deal. Even taking into account that FiveThirtyEight couldn't have been perfectly accurate in their talent assessments, it's still not that big a deal. If they were off, on talent, by around 3 games per team, that would bring them to only about 1.5 SDs of luck.

Still not a huge deal, but interesting nonetheless.

------

It wasn't just FiveThirtyEight whose projections did well ... the Vegas bookmakers did OK too. Well, at least the one I looked at, Bovada. (I assume the others would be pretty close.)  They had an SD of 5.5 games, which is also better than the "speed of light."  (I can't find the page I got them from, but this one, from a month earlier, is close.)

That suggests that it probably wasn't any particular flash of brilliance from either FiveThirtyEight or Bovada ... it must have been something about the way the season unfolded. 

Maybe, in 2016, there was less random deviation than usual? One type of random variation is whether a team exceeds their Pythagorean Projection -- that is, whether they win more (or fewer) games than you'd expect from their runs scored and allowed. To check that, I used Baseball Prospectus's numbers -- specifically, the difference between actual and "first-order wins."***

(*** Why didn't I use second-order wins? See the P.S. at the bottom of the post.)

In the National League in 2016, the SD of Pythagorean error was 3.55. That is indeed a little smaller than the average of around 4.0. But that small difference isn't nearly enough to explain why the projections were so good.

Here's what I think is the bigger factor -- actually, a combination of two factors.

First, by random chance, the better teams happened to undershoot their Pythagorean expectation, and the worse teams happened to exceed it. 

The Cubs were the best team in the league, and also the team with the most bad luck, -4.8 games. The Phillies were the worst team in the league with luck removed; you'd expect them to have won only 61.4 games, but they but played +9.6 games above their Pythagorean projection to go 71-91.

Those two were the most obvious examples, but the pattern continued through the league. Overall, the correlation between first-order wins (which is an approximation of talent) and Pythagorean error was huge: +0.61. Normally, you'd expect it to be close to zero. (In the American league, it was, indeed, close to zero, at -0.06.)

Second, there was a similar, offsetting relationship in the predictions themselves. 

It turns out that the forecast errors had a strong pattern this year.  Instead of being random, they came out too "conservative" -- they underestimated the talent of the better teams, and overestimated the talent of the worse teams. Here's the distribution of FiveThirtyEight's forecast errors, with the teams sorted by their forecast:

Top 5 teams: average error -4 wins (underestimate)
Mid 5 teams: average error +4  win (overestimate)
Btm 5 teams: average error +1  win (overestimate)

So, in summary:

-- FiveThirtyEight predicted teams too close to the mean
-- Teams' Pythagorean luck moved them closer to the mean

Those two things cancelled each other out to a significant extent. And that's why FiveThirtyEight was so accurate.

-------

Next post: The American League, which is interesting for completely different reasons.

-------

P.S. Baseball Prospectus also produces "second-order wins," which attempts to remove a second kind of luck, what I call "Runs Created luck" (and others call "cluster luck"), which is teams scoring more or fewer runs than would be expected by their batting line. I started to do that, but ... I stopped, because I found something weird.

When you remove luck from the standings, you expect to make them tighter, to bring teams closer together. (To see that better, imagine removing luck from coin tosses. Every team reverts to .500.)

Removing first-order (Pythagorean) luck does seem to reduce the SD of the standings. But, removing second-order (Cluster) luck seems to do the *opposite*.

I checked four seasons of BP data, and, in every case, the SD of second-order wins (for the set of all 30 teams) was higher than the SD of first-order wins:  

         Actual  First-order  Second-order
------------------------------------------
2016      10.7        10.8        13.1
2015      10.4        10.1        11.8
2014       9.6         8.9         9.6
2013      12.2        12.2        12.8

So, either the good teams got lucky all four years, or there's something weird about how BP is computing second-order luck.