Euro 2016 – full projection

After creating attack and defence ratings for the 24 Euro 2016 teams, based on their underlying squad strength (as described here), I can run simulations to look at the likelihood of different tournament outcomes, including the winner. My projection simulates the score of each match for 5000 different possible tournament outcomes – including potential extra time and penalties in the knockout stages.

One of the main differences from my domestic league projections is that most matches are played at a neutral venue; the one exception is obviously France, so I’ve applied a 0.38 goal increase to allow for their home field advantage (i.e. 0.19 added to expected goals scored, 0.19 deducted from expected goals conceded).

I’ve also allowed for typical tournament scoring patterns as I described in this article.

The model’s projected likelihood of wining Euro 2016 is as follows:

eurowin

euroround

This shows France as clear favourites, despite Spain’s ranking as the top team from my rating system. However, France’s home field advantage tips the balance in their favour.

Comparing these probabilities with Market odds (implied probability using max odds from oddschecker.com) identifies where my model differs from the market. Most teams are very close to my model, including the favourites France. But there are some clear inconsistencies. The major outlier is Germany; the market has them at 18% to win, whereas my model is 11%. Germany don’t appear good value (although it’s always dangerous to bet against Germany!). To a lesser extent, the same applies to the much-fancied Belgium.

eurowinvalueEurovalue

Where is there value? According to my model, we need to look to the Iberian Peninsula for Euro 2016 winner value. Portugal and, in particular, Spain – both look good value.

What about England? Based on my ratings England are the 4th ranked team (2nd best attack but only 8th best defence). Although such a high rank feels contrary to my experience of watching England in tournament football, this ranking is also consistent with market odds. And, my model actually suggests that England are poor value, with market probability of 10% compared with a modelled likelihood of 8%. So my main tournament betting rule – always bet against England – appears to apply to Euro 2016 too.

Next up

Group betting and more detailed analysis

Previous Euro 2016 articles

Euro 2016 – Assessing international teams

Euro 2016 preview 1 – how goal patterns repeat in international tournamentsEuro 2016 preview 1 – how goal patterns repeat in international tournaments

Euro 2016 – Why England’s most likely last 16 opponents are Germany.

 

Advertisements

One Comment Add yours

  1. FPL says:

    It’s all about France & Portugal in the group stages for me.

    Like

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s