Matter of Stats

View Original

2017 : Simulating the Final Series After Week 2 of the Finals

The Cats' and Giants' victories on the weekend mean that 30 of the last 36 Preliminary Finalists will have been teams that have had the double-chance, and also that we'll have 1st v 2nd in one of the Prelims, and 3rd v 4th in the other.

Our simulations involve generating predictions for those two contests and for the Grand Final matchup they will determine by applying the methodology as described in this blog.

In the chart below we record the proportion of the 10,000 simulations in which a particular team went out in a given week of the Finals.

The weekend's results were, according to the simulations, most beneficial for the two victors, though they find themselves ranked 3rd and 4th in terms of Flag chances. On a team-by-team basis, the changes in Flag chances this week were as follows:

  • Geelong +12%
  • GWS +8%
  • Adelaide +1%
  • Richmond -1%
  • West Coast -4%
  • Sydney -15%

The newly estimated probabilities of going out in a particular week are shown in the heatmap below.

This week, as I did last week, I'm also going to present the results of the simulations in which the on-the-day rating perturbations are set to zero.

Using this alternative approach, we have the following:

This method lifts Adelaide's chances by a little over 6% points, and Richmond's by a little over 1% point. It also drops Geelong's chances by about 4.5% points, and GWS' by a little over 3% points.

As a heatmap we have.

So, once again being conservative, we might conclude that the Flag chances of each team lie in the following ranges:

  • Adelaide 34-40%
  • Richmond 28-29%
  • Geelong 16-20%
  • GWS 15-19%

As a last output, let's again look at the underlying team-versus-team probabilities that fall out of the two simulation approaches. The first set of probabilities relate to the simulations we looked at first in this blog and you can see that, as I noted last week, they tend to be nearer 50% than the second set of probabilities, which come when we remove the perturbations.

If these estimates are correct, even the most mismatched of Grand Final pairings would see Adelaide start as about $1.50 favourites over GWS.