This week saw some large changes in teams' chances for Top 4 and Top 8 spots as the number of rounds remaining shrank to three.

Overall, this week's 50,000 simulations of the remainder of the 2017 AFL season sees:

• six teams' Finals chances move by more than 5% points
• five teams' Finals chances move by more than 10% points
• six teams' Top 4 chances move by more than 5% points
• five teams' Top 4 chances move by more than 10% points

(For details on the methodology I've used in the simulations, please see this blog.)

RESULTS

The charts below summarise the distribution of ladder finishes for the 18 teams from the simulations run after the current round, Round 20, and Round 19. Note that the ordering of the teams is slightly different in the two charts, reflecting improvement or deterioration in some team's expected ladder finish.

In terms of Final 8 chances, the big winners this week were:

• Sydney: +13% points
• Western Bulldogs: +13% points (up by 35% points now in the last three weeks)
• Essendon: +10% points
• St Kilda: +5% points

The big losers were:

• Melbourne: -20% points (down by 34% points now in the last two weeks)
• West Coast: -17% points

In terms of Top 4 chances, we had as winners:

• GWS: +19% points (up by 24% points now in the last two weeks)
• Richmond: +18% points (up by 54% points now in the last three weeks)
• Sydney: +13% points

... and, as losers:

• Port Adelaide: -29% points
• Geelong: -13% points
• Melbourne: -8% points

We see yet more narrowing in the range of ladder finishes for most teams this week, but the uncertainty over mid-table finishes remains.

Speaking of uncertainty, what do the new Gini coefficients for teams and ladder positions tell us? (see last week's blog for some detail on what Gini coefficients are and how to interpret them).

From a team-by-team perspective we see that every team except Collingwood and Geelong became more certain about their final ladder positions after Round 20, but there still remains considerable uncertainty about the finishes for Port Adelaide, St Kilda, West Coast, Essendon, Melbourne, and the Western Bulldogs.

Port Adelaide has 10% or larger chances of finishing anywhere from 4th to 8th, St Kilda from 8th to 12th, West Coast from 8th to 11th, Essendon and Melbourne from 7th to 11th, and the Western Bulldogs from 6th to 10th.

The teams enjoying the largest increase in the level of uncertainty surrounding their final ladder position were:

• GWS - now over 75% likely to finish 2nd to 4th
• Richmond - now over 75% likely to finish 2nd to 4th
• Sydney - now about 70% likely to finish 4th to 6th
• Hawthorn - now over 80% likely to finish 11th to 14th

Most of the uncertainty for teams surrounds ladder positions from about 6th to 11th, and it's these positions that also show up as having the smallest Gini coefficients when we take a ladder finish perspective. Seventh remains the ladder spot with the highest level of uncertainty, followed by 6th and 8th.

The uncertainty surrounding every position shrunk at least a little this week, though especially for 5th (Sydney and Port Adelaide now 50% chances, combined), 3rd (GWS, Richmond and Geelong now accounting for over 75% of the replicates), and 14th (Fremantle now about a 64% chance).

1st and 18th remain the positions about which there is most certainty.

GAME IMPORTANCE

Next, let's update the game importance table. It shows, you'll recall, how each team's chances of making the finals varies depending on the result of each of the remaining games. The overall Weighted Ave Importance figure tells us the average amount by which the teams' finals chances are expected to change on the basis of the outcome of a particular game. A larger figure means that the game is expected to change teams' finals chances, on average, by a larger amount and hence is a more important game.

(For more details about the methodology and the rationale for it, again please see this blog.)

Three very influential games are in prospect in Round 21:

• Melbourne v St Kilda, which predominantly affects the chances of only these two teams
• Essendon v Adelaide, which materially affects the chances of Essendon and Adelaide, but also St Kilda, West Coast, and the Western Bulldogs
• Western Bulldogs v GWS, which materially affects the chances of the Western Bulldogs and GWS, but also Essendon, Melbourne, St Kilda and West Coast

Of the remaining games, only the West Coast v Carlton game is of any likely consequence.

NUMBER OF WINS REQUIRED

Next, an update on the analysis looking at how likely it is that a team will play Finals given that it finishes the home-and-away season on exactly 11, 11.5 or 12 wins.

Recall that these estimates, because they're based on a sample of simulations, are subject to error (as are all of those in this blog), which here is reflected in the width of the segment.

The upshot of this chart is that, to have at least a 50% chance of playing Finals requires:

• At least 1 more win: Port Adelaide and Sydney
• At least 2 more wins: Western Bulldogs, Essendon, West Coast, and Melbourne (and 2 wins only gets West Coast to about 50%)
• 3 more wins: St Kilda

If we look, instead, at Top 4 finishes and winning between 13 and 14 games, we have the following.

In short, it looks like a minimum of 14 wins will be needed for a Top 4 finish, and that gives every team except the Dogs a 75% chance or better of such a finish. The Dogs will need three wins and some luck to finish Top 4.

MOST LIKELY TOP 2s and top 4s

This week we'll again look at the team orderings most likely for the Top 2 and Top 4 spots.

Based on the latest simulations, the most likely final Top 2 is now Adelaide/GWS, the previous most likely pairing of Adelaide/Geelong slipping to 3rd.

Combined, the three most likely pairings of Adelaide plus one of GWS, Richmond and Geelong account for about 85% of all replicates. If we add in the mirror-images of each pairing, we account for all but about 5% of the replicates.

The most likely Top 4 is now Adelaide/GWS/Richmond/Geelong, which occurred in just over 12% of replicates and is the same top quartet as we had last week, though with the Cats slipping from 2nd into 4th.

The six most likely Top 4s all contain those same four teams but in different orderings. They account for about 38% of replicates.

Sydney or Port Adelaide join the Top 4 in the four other most likely orderings, at the expense of either Richmond or Geelong.

SIMULATIONS OF THE FINALS SERIES

Applying the methodology as described in this blog to the 50,000 final ladders produced by our original simulations yields the following results.

The altered fortune of Port Adelaide is probably the most striking feature of this chart this week, especially in terms of its ability to win the Flag from outside the Top 4. It does this now only about 3.6% of the time it finishes 4th to 8th. By way of contrast, the Swans complete this feat about 9% of the time, and Geelong, GWS and Richmond do it between 4.4% and 4.8% of the time.

Altogether, a team from outside the Top 4 wins the Flag in 17% of replicates, and a team from outside the Top 4 finishes as Runners Up in 20% of replicates. That's very much in keeping with the closeness of this season's competition.

Adelaide remain favoured by the simulations to take out both the Minor Premiership (87% chance) and the Flag (35% chance). GWS has about a 6% chance for the Minor Premiership and a 13% chance for the Flag, while Richmond, Geelong and Sydney all have about 12 to 14% chances for the Flag. Port Adelaide's Flag chances have slumped to around 5%.

We see from the heatmap above that, if we define the season in terms of the six events listed there, the most-likely finishes for each team are estimated to be:

• Win Grand Final: Adelaide
• Lose in a Preliminary Final: GWS, Richmond and Geelong
• Lose in a Semi Final: Sydney
• Lose in an Elimination Final: Port Adelaide
• Miss the Finals: all other teams

We also see that Adelaide are estimated to be about 57% chances for making the Grand Final, GWS and Richmond about 30%, and Geelong and Sydney about 26% to 27%. Port Adelaide are now only about 12% chances and the Dogs just 7% chances of playing in back-to-back Grand Finals.