With the 2017 season being such an open one, many teams' chances fluctuate significantly after every game.

With the 2017 season being such an open one, many teams' chances fluctuate significantly after every game.

This week's 50,000 simulations of the remainder of the 2017 AFL season again see eight teams' Finals chances move by more than 5% points.

The latest set of 50,000 simulations of the remainder of the 2017 AFL season saw 8 teams' Finals chances move by more than 5% points.

The latest set of 50,000 simulations of the remainder of the 2017 AFL season suggest that Round 13 provided relatively little fresh evidence for most teams to help answer the question "will they play finals?".

Every year I try to delay running ladder simulations until later in the season, and every year I wind up starting them earlier and earlier.

It seems a bit grandiose to dub the work summarised in this blog as a "simulation" since, with just three games to go, all that's been required to assemble it has been six probability assumptions: two for the Preliminary Finals and four for the possible Grand Final matchups.

Geelong are narrow favourites for the Flag according to the latest set of 100,000 simulation replicates based on MoSSBODS' Team Ratings and on its assessments of the remaining teams' abilities at the venues they might inhabit over the remainder of the Finals series.

You could argue - and I'd probably not have a strong rebuttal for you - that MoSSBODS has been overestimating the Crows' Flag chances for a while now, but whether or not that's true I think it's objectively apparent their unexpected loss last weekend caused those chances to reduce dramatically.

The outputs of this week's simulation run starkly highlight the differences between MoSSBODS' and the TAB Bookmaker's opinions about a number of teams that will play in the Finals.

Perhaps more than in any recent season, there's still of lot of "conditionality" in the final home-and-away season ladder, by which I mean that knowing where Team A finishes tells us a lot about the likely finishes of other teams.

A loss by GWS and a lacklustre performance by Geelong saw both teams' chances of the Minor Premiership decline significantly this weekend, in GWS' case into near non-existence.

MoSSBODS right now is very much a Crows fan - some might say too much of a fan - and that enthusiasm reveals itself quite clearly in the results of the latest simulations.

I'm fairly sure it'll not be entirely surprising to you when I say that this week's results put a significant dent in the Top 4 aspirations of Adelaide and the Western Bulldogs, bolstered the Finals hope of the Roos at the Saints' expense, and made the Dons more likely Wooden Spooners and the Lions less likely to collect that item of cutlery.

The Roos did just about enough this weekend to secure the final spot in the 8, though an upset victory over the Dogs and Port Adelaide's loss to the Giants, left a very small door open for the Saints. They're now 14% chances of taking that last place while the Kangaroos are 84% chances.

From a "who plays the Finals" point of view, last week's results were most encouraging for Port Adelaide (+14%) and St Kilda (+6%), and least encouraging for the Kangaroos (-21%).

Geelong's loss to Sydney this week put a considerable dent in their Minor Premiership prospects, at least according to the latest MoSSBODS-based simulations (see last week's post for details of how these simulations are performed)

This week, I've used the same methodology as I did last week, but expanded the number of simulations to 100,000, which means I've doubled the precision relative to last week's estimates (since four times the number of simulations provides twice the precision). It took about 7 hours to run the simulations, but that's a small price to pay for added precision (he offers, self-affirmingly ...)

This year I'm starting simulations for the Finalists a bit earlier than usual, partly as a result of a request from Twitter follower @SgtButane, who's another of the burgeoning group of AFL fans using statistical modelling techniques to forecast game outcomes. If you've an interest in this sort of modelling and you're not yet on Twitter, I'd strongly encourage you to sign up and start following like-minded people (I'm @MatterOfStats by the way). There's a tremendous amount of informed commentary and quality analysis being shared by some very talented people in this space.

After Week 1 of the Finals, six teams are still capable of winning the Flag and nine Grand Final pairings are still possible.