2018 : Simulating the Finals Series After Round 24 (Week 1 of the Finals)
/MoSHBODS was right about all four games in Week 1 of the Finals, and its thoughts about the remainder of the Finals series are embodied in the latest simulation outputs (which use the methodology described here but, again, with no perturbation of the current offensive and defensive ratings) a summary of which appears below.
Again this week, rather than colour-coding the chart by a team's final ladder position, we've instead colour-coded by the opponent they lost to or, in the case of the "Win GF" bars, the opponent they defeated.
We see that Richmond remain Flag favourites, with an estimated probability now of around 44%. We also see that the majority of those Grand Final wins come against West Coast, some more against Melbourne, and just a handful against Hawthorn.
Melbourne are now second favourites according to the simulations, just slightly ahead of West Coast. Melbourne's Grand Final victories come mostly from Richmond, occasionally from Collingwood, and less rarely still from GWS. The profile of West Coast's Grand Final triumphs is very similar to Melbourne's.
WEEK OF ELIMINATION IN FINALS
In this next chart we look at teams' chances for various Finals finishes (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 (or achieved the specified result).
(Note that 0 entries reflect estimated probabilities greater than 0% but under 0.05%).
Richmond, as noted, are assessed as just over 44% chances for the Flag, up about 4% points from last week, and about 68% chances of playing in the Grand Final, up by about 10% points. Melbourne are about 19% chances, West Coast 18%, and Collingwood 10%.
Hawthorn are assessed as having the smallest chances of all at just under 3.9%,
Based on the latest TAB markets for the Flag, the only team offering value given the probability estimates here is Melbourne, who are currently at $6.
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.
(Note that 0 entries reflect estimated probabilities greater than 0% but under 0.05%).
Only nine pairings are now possible, and all but three of them have estimated probabilities less than 10%.
The Grand Final pairing of Richmond v West Coast is most common, and now appears in more than one-third of replicates. Next is Richmond v Melbourne, which appeared in roughly one-quarter of replicates, and then West Coast v Collingwood, which appeared in roughly one replicate in 10.
