2019 : Simulating the Final Ladder After Round 20

/

The results of the latest 50,000 simulations appear below.

(If you’re curious about the methodology used to create them, you can start here.)

RESULTS

Last weekend’s results essentially locked in 6 of the 8 Finalists according to the latest simulation results, and left Essendon with an estimated 80% chance of a berth, Adelaide with a slightly better than even-money shot, and Port Adelaide with a slightly worse than even-money shot at playing into September. Five other teams have mathematical chances, the best of them the Western Bulldogs, who make the Finals in 11% of simulation replicates.

In the race for the Top 4, three teams have 84% chances or higher, Richmond is about a 2 in 3 shot, GWS a 1 in 2 shot, and Collingwood a 3 in 20 shot. Essendon and Adelaide have chances too, but they need to be preceded with the adjective “vanishingly small”.

Geelong are now estimated to be only 44% chances for the Minor Premiership, and the Brisbane Lions 36% chances.

In terms of estimated probability of making the Finals, the largest moves this week were:

BIGGEST LOSERS

  • Essendon (down 15% points to 80%)

BIGGEST GAINERS

  • Port Adelaide (up 26% points to 44%)

The week saw only small changes in teams’ Top 4 prospects, the largest of them being Essendon’s 8% point decline, and Richmond’s 7% point increase.

DETAILED LADDER FINISH ESTIMATES

The detailed view of each team’s estimated probability of finishing in each of the 18 possible ladder positions appears below. Blank cells represent ladder finishes that did not occur even once in the 50,000 simulations, while cells showing a value of 0 represent estimated probabilities below 0.05%.

The narrowing of the range of possible ladder finishes for most teams is apparent this week, with most fuzziness remaining for the teams currently in 10th to 13th, which we’ll return to in a moment.

WINS REQUIRED FOR TOP 8 AND TOP 4

Port Adelaide and Adelaide are the only teams with better than 1 in 4 chances of playing Finals should they finish on just 11 wins, and St Kilda essentially have no chance even if they end the season with 3 straight wins.

Aside from Adelaide and Essendon, for whom 11.5 wins will be sufficient, all other teams will need at least 12 wins to be estimated 75% chances or better of playing Finals.

The estimated probability of the team in 8th spot finishing with just 10 wins fell significantly this week to 0.5%, or about 1 in 200.

Fourteen wins still gives the seven teams capable of registering that many a very wide range of estimated chances of finishing Top 4, but they all have lower estimates of doing so than were determined after Round 19. Geelong’s chances are now roughly 40% with such a finish, GWS’ around 30%, and the remaining teams’ all less than 10% (including Essendon’s near-zero estimate).

With fifteen wins, Geelong and GWS are virtual certainties for a Top 4 finish, while West Coast, Brisbane Lions, Richmond and Collingwood are all about 65 to 75% chances.

The most-likely tally of wins for teams in various final home-and-away ladder positions are now:

  • 1st: 16 or 17 wins

  • 2nd: 16 wins

  • 3rd and 4th: 15 wins

  • 5th: 14 wins

  • 6th: 13 or 14 wins

  • 7th: 12 wins

  • 8th: 11 or 12 wins

  • 9th: 11 wins

  • 10th: 10 or 11 wins

  • 11th and 12th: 10 wins

  • 13th and 14th: 9 wins

  • 15th: 8 wins

  • 16th: 7 wins

  • 17th: 6 wins

  • 18th: 3 wins

TOP 2s AND TOP 4s

This week, again, we’ll look at what the simulations are suggesting are the most-likely combinations of teams finishing in key positions.

For Top 2s, this week we have the situation as shown at right, which still sees a Geelong-Brisbane Lions 1-2 finish the most likely, but with it now occurring in only 18% or replicates. A Brisbane-Geelong finish is now the next most-likely, it occurring in about 1-in-6 simulations, just ahead of Geelong-West Coast, Brisbane-West Coast, and Geelong-Richmond finishes.

No other pairing has an estimated probability above 8%.

Across all 10 of the combinations shown here, five different teams appear at least once: Geelong, Brisbane Lions, West Coast, Richmond, and GWS. Combined, the 10 combinations represent 96% of all of the simulations.

Looking next at Top 4s, we see that even the most-likely combination appears in less than 5% of simulations, that being for a Geelong-Brisbane Lions-West Coast-Richmond finish. It’s just ahead of a slew of similarly-likely finishes, first of which is a Brisbane Lions-Geelong-West Coast-Richmond finish, which occurred in 3.9% of simulations.

Six other orderings appeared in 3.4% or more of the simulations.

Across all 10 of the combinations shown here, five different teams appear at least once: Geelong, Brisbane Lions, West Coast, Richmond, and GWS. Combined, the 10 combinations represent only 35% of all of the simulations.

In terms of the Top 8, there were 5,950 different orderings this week across the 50,000 simulations. If we ignore order, we find 31 unique combinations of teams in the Top 8s across the simulations, the most commonly occurring set being the eight teams currently filling the Top 8 spots on the ladder, which turned up in about 38% of simulation replicates, just ahead of the combination that swaps in Port Adelaide for Adelaide, which turned up in about 29%. The third most-likely combination had Port Adelaide substituting Essendon and occurred in just over 10% of replicates.

LIKELIHOOD OF PERCENTAGE DETERMINING POSITIONS

This week’s results served to make it more likely that some key positions on the final home-and-away ladder will be determined by percentage because the teams in those positions finish tied on competition points.

In the latest simulations, 4th and 5th are separated by percentage in about 46% of the simulations (down 1% points), and 8th and 9th are separated by percentage in about 50% of the simulations (up 8% points). As well, 8th and 10th are separated by percentage in about 24% of the simulations, and 8th from 11th in about 8%.

Also, in just under 1 simulation in 2, 1st and 2nd are separated only by percentage.

TEAM AND POSITION CONCENTRATION

One way of measuring how much uncertainty there is in the competition is to use the Gini measure of concentration commonly used in economics for measuring income inequality to quantify the spread of each team's estimated final ladder positions across the 50,000 simulation replicates, and to quantify the concentration in the probabilities across all the teams vying for any given ladder position.

This week saw the uncertainty about the final ordering of the teams decrease quite significantly again, with the Gini coefficients rising to around 0.78.

At the team level, we saw reductions in uncertainty for all but Geelong, the biggest reductions being for St Kilda and Port Adelaide.

Fremantle, Western Bulldogs, North Melbourne, Hawthorn, and Richmond now have the most uncertainty, while Gold Coast, Melbourne, Carlton, and Sydney have the most certainty about their eventual ladder finishes.

If we adopt a ladder position viewpoint instead, we see that 1st and 18th as still amongst the positions with the narrowest range of likely occupants, though they are now joined by 15th, 16th and 17th.

All 18 positions except 1st, 2nd, 3rd, and 10th saw increases in certainty, the largest for positions 13th, 14th and 15th. The positions with most uncertainty are 9th through 13th.

Roughly speaking, we have slightly more certainty this year after 20 rounds than we did last year at the same point about the final ordering of the teams at the end of the home-and-away season (the Gini coefficient then was about 0.77).

GAME IMPORTANCE

Here are the assessments of importance for the remaining 27 games of the home-and-away season. (See this blog for details about how these are calculated.)

Adelaide are now involved in two of the top 3, and Port Adelaide in three of the top 6. The Western Bulldogs are also involved in two of the Top 5. In total, only the Top 10, or maybe 11, games likely have a significant impact on the Final 8.

To finish we’ll again look at the importance of the remaining games in terms of their estimated likely impact on the Top 4 (using an equivalent methodology to that we used for assessing the likely impact on the Top 8).

Here, we find Richmond are involved in two of the Top 3 games, and GWS in three of the Top 5. In total, only the Top 11, or maybe 14, games likely have a significant impact on the Final 4.