Here we are with only four matches left for most teams (Tottenham and Man City being the exception, since their match was postponed until May due to the FA Cup). Even at this late stage, there is still ambiguity about who will end up where, and there are some massive games ahead.
As always, for some background on how these numbers are derived (and why, other than because your author is a big fat nerd), please check this backgrounder.
As of April 28 (up to and including Fulham’s 3-0 defeat of Bolton), the probabilities of each team achieving each position in the league table are as follows:
The table above shows the number of times over 10,000 simulation runs that a particular team ends up in a particular position at the end of the season. The number in red indicates that team’s most likely outcome. There is very little variation at the top of the table, but far more ambiguity in the middle and at the bottom. The chart provides the same information in graphical form (sorry for the quality, best I could do in Excel).
As in the last post, these numbers can be used to determine some rough probabilities.
League Title Race — is over. It has been over for a while, but Arsenal’s recent “form” (I’m using the term loosely) has dumped them out of a race that was never very close to begin with. A month ago the simulation calculated a 20% chance of pipping Man Utd for the lead. Now, just 6 times in 10,000 did some combination of wins for them and failures for everybody else move them to first. Chelsea, now in second in the league, has about 19-1 odds of winning but of course, the numbers don’t lie and it’s the Red Devils who will be the overwhelmingly likely winners.
Top 6 teams – The most likely ordering for the top 6 is Man Utd, Chelsea, Arsenal, Man City, Tottenham, and Liverpool. Not only do the simulation runs show each team with a high individual probability of being ranked in this order (Chelsea was 2nd 75% of the time, Spurs in 5th 73%, etc), but jointly, 39% of the simulation runs ended with the six teams in that order.
Champions League – Tottenham’s hopes are more or less over at this point; While they did creep into the top 4 in 8.7% of all runs, the more likely outcome is 5th. On the plus side, this means European football is not out of reach. Man Utd, Chelsea, and Arsenal overwhelmingly made it into the top 4, While Man City clinched the run-off spot 92% of the time.
Relegation — More big changes. In late March when I first ran the simulation (though didn’t write it up on the blog) Wigan was in very big trouble indeed, with a 75% chance of being relegated. The Latics are still in big trouble but West Ham, which at the time had only a 35% chance of relegation, have now hit the bottom of the table hard and it is difficult to see how they will be able to get out of the abyss with just 4 games left in the season. The “W” curse seems alive and well with Wigan (64%) and Wolves (68%) joining the Hammers in the drop zone. Blackburn (29%) and Blackpool (59%) are hovering but just outside.
The First-Year Curse — Last year it was West Brom, Blackpool, and Newcastle coming up from the Championship. Blackpool still has better than even odds of being relegated, but there is a 41% chance that all three promotion teams from last year will stay up.
Impact of Specific Games — I picked three upcoming games and analyzed how the likelihood of winning or being relegated changed as a result of the single game outcome.
Arsenal hosts Man Utd at the Emirates this weekend, and all pundits seem to think that a Red Devils win will clinch the title. While the probability is indeed very likely, a Manchester win does not mathematically clinch it for them; there are still scenarios that have other teams coming out on top. However, since the match is on Sunday, it’s quite possible that Saturday’s outcomes will set up a Sunday league win for the away team in North London.
Stoke is in no danger of relegation, but they can certainly affect the fortunes of the Tangerines on Saturday. A Blackpool win would decrease their chances of relegation to 38%; but if they draw or lose, the likelihood of Championship football next season goes up (to 69% and 82% respectively).
In a couple of weeks, the fight at the bottom will be the matchup between Wigan and West Ham at the DW. Based on the simulation today, the outcome of the game is massive for both teams. A Wigan win means a 40% chance of relegation for them and 93% for West Ham. A draw makes things worse for Wigan (72% chance of relegation) and West Ham (80%). Finally, a rare away win for the Hammers would reduce their chances of the drop to 50% while increasing Wigan’s to 87%.
As always I welcome comments or criticisms. Enjoy!