More World Cup Economics and Econometrics (or Quants)

Nick’s beaten me to posting about the World Cup predictions of large financial institutions, but I’ll follow on from there.  We’re now just over 24 hours until the World Cup starts with Mexico taking on the hosts, South Africa.

As mentioned, a number of large financial corporations have placed their hat in the ring to forecast who will win the World Cup, and of course also who will be the big winners economically.  Chances are it won’t be South Africa, but that’s another blog post or two.

Anyhow, from the FT we find that Danske Bank picked Brazil based on a quants model (to the best of my ignorance, quants model basically means some form of econometric model to the rest of us?), UBS followed suit with the South Americans although JP Morgan bucked the trend and picked England to win.  If you’re interested, you can take part in a competition to try and beat the predictions of the banks here.

I have decided to make some predictions, and to use econometrics and data to do so.  I’ve estimated an ordered probit model based on around 3000 historical football matches (a whole range of competitions including importantly the qualifiers from all regions of the world).  Perhaps unsurprisingly I find that Brazil wins – beating Spain in what would be a tasty final.  England make the semi-finals, as do Germany (England losing to Brazil, Germany to Spain in a re-run of the Euro 2008 final).

Of course, this is all conjecture and probability.  We shall see who comes out on top and which model is best.

On to South Africa vs Mexico though.  Nick fancies Mexico, and I do too based on my model: It gives them a 56% probability of winning, South African only a 24% probability of winning.  But Betfair isn’t so sure: As of 11am British Summer Time, Mexico are at 36%, with South Africa at 34% (probabilities implied from the decimal odds there).  I’ve done a fair bit of research on Betfair (which will hopefully be published soon), and their implied probabilities are usually very accurate indeed.

Are they able to better take into account factors such as the first World Cup on African soil, those horns the fans will be blowing, and all the other emotions associated with a World Cup that mean events like Cameroon beating Argentina in 1990 and Senegal beating France in 2002 can happen?  We shall soon see…


Leave a Reply

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

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

Google+ photo

You are commenting using your Google+ 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 )


Connecting to %s

%d bloggers like this: