2022 : Simulating the Finals Series After Round 16
/Time to take another look at Finals simulations.
(For details about the methodology, see this blog post and also refer to this one from last week that talks about an alternative approach to adding time-based variability to team ratings that I’m currently trialling)
Applying the “traditional” methodology to 10,000 of the 50,000 home and away season simulation replicates yields the following chart showing teams’ Finals fate overall and as a function of their ultimate ladder position at the end of the home and away season.
Overall, we see that the teams fall fairly naturally into seven groups:
Melbourne and Geelong: about 20% chances for the Flag and about 40% chances to make the Grand Final
Brisbane Lions: about 15% chances for the Flag and 30% chances to make the Grand Final
Fremantle, Collingwood and Sydney: about 8-12% chances for the Flag and 15-20% chances to make the Grand Final
Carlton and Richmond: approximately 5% chances for the Flag and 10% chances to make the Grand Final
Western Bulldogs and St Kilda: approximately 2-3% chances for the Flag and 5-7% chances to make the Grand Final
Gold Coast and Port Adelaide: less than 1% chance for the Flag and about 1-2% chances to make the Grand Final
The Rest: all less than 0.5% chances to make the Finals and effectively zero chance of making the Grand Final
We also can see that Melbourne and Geelong are the only teams that win more than 50% of the Grand Finals that they make.
WEEK OF ELIMINATION IN FINALS
In this next chart we look at teams' chances for various Finals finishes, ignoring their home and away ladder positions (ie we focus solely on the heights of the bars in the previous chart). The numbers shown inside a cell are the percentage of simulation replicates (multiplied by 100) in which the specified team went out in the specified week of the Finals.
We see here that, if we define the season in terms of the five events listed above plus "Miss the Finals", the most-likely finishes for each team are estimated to be:
Lose in a Preliminary Final: Melbourne, Geelong, and Brisbane Lions (but note that Melbourne and Geelong are both more likely to make the Grand Final than to lose in a Preliminary Final)
Lose in a Semi Final: Fremantle (just)
Lose in an Elimination Final: Collingwood, Sydney, Carlton, and Richmond
Miss the Finals: all other teams
GRAND FINAL PAIRINGS
In this final chart we look at all of the Grand Final pairings that occurred in at least one of the simulation replicates. The numbers shown inside a cell are the percentage of simulation replicates (multiplied by 100) in which the team named in the row defeated the team named in the column in the Grand Final.
We see that the most common Grand Final has Geelong defeating Melbourne. This occurred in just over 5% of replicates. The opposite result - Melbourne defeating Geelong - occurred in another 5% of replicates.
(Note that zeroes in the chart represent pairings that did occur at least once but in less than 0.05% of replicates.)
CHARTS FOR THE ALTERNATIVE METHOD
Applying the alternative methodology to both the home and away season simulations and then to 10,000 of those for the purposes of simulating the Finals yields the following, alternative outputs.
As we saw last week, this methodology significantly improves the results for the strongest teams (here Melbourne and Geelong), and generally does the opposite for the remaining teams.
Overall, the team-by-team main differences are:
Melbourne’s Flag chances increase from about 22% to 30%
Geelong’s Flag chances increase from about 20% to 25%
Brisbane Lions’ Flag chances decrease from about 15% to 11%
Fremantle’s Flag chances decrease from about 11% to 7%
Collingwood’s Flag chances decrease from about 8.5% to 7%
Sydney’s chances are broadly unchanged
Carlton’s Flag chances decrease from about 5% to 3%
Richmond ’s Flag chances decrease from about 5% to 4%
St Kilda’s Flag chances decrease from about 2% to 1%
Western Bulldogs’, Gold Coast’s, and Port Adelaide’s chances are broadly unchanged
For completeness’ sake, here are the Grand Final matchup numbers under this alternative methodology:
The Melbourne v Geelong Grand Final now turns up in almost 16% of replicates, which is about half as much again as under the earlier methodology.
(As an interesting aside, I had some challenges creating this chart because GWS appear only once in the 10,000 simulated Finals series … and then win the Flag. That’s why they appear on the y-axis, but not the x-axis)
