Certified Legendary Thread Race for the flag, in squiggly lines

[QuietB]

Hawthorn are going to get dizzy going around in circles like that.

 

[TBellicious]

Tremendous week for the Lions.

 

[TBellicious]

The Bulldogs will finish higher than the Giants this year.

 

[The Swans Blog]

Also i would like to know what total tips the squiggle is on this year?

ISTATE 41 total tips - http://www.bigfooty.com/forum/threads/afl-prediction-models-round-7.1094371/

 

[threenewpadlocks]

Final Siren can I ask do you have any way to provide a value of what a team needs to score to improve their predicted win tally for the rest of the season season, accounting for the lost "decimal" wins for the current game? For example, Fremantle are predicted to beat North 98-70 and North are expected to gain 0.2 wins for the purposes of the ladder predictor. If that is the exact margin of the game, North's position on the squiggle won't change, but they'll "lose" the 0.2 wins and therefore drop 0.2 wins on the ladder predictor. Therefore is it possible to provide get a figure or calculation of what North would need to score (as a % of Freo's score because that's how the squiggle works) to improve their total predicted wins because of an improved squiggle for the rest of the season even accounting for the lost "decimal" wins so to speak. If North were to lose by 1 point, they might lose the 0.2 wins, but with the improved squiggle position, they'd gain the .2 back over the remaining 14 games of the season, plus some more wins and improve their overall ladder position despite the loss. It's an "equilibrium" figure so to speak, and it'll be obviously more dramatic as the season goes on. It also won't work for all games, like GWS being predicted to beat Adelaide by three points and getting 0.55 wins. I don't think Adelaide will make up the "loss" of 0.45 wins by an improved squiggle position by only losing by 1 or 2 points and doing better than the squiggle prediction by only 1 or 2 points.

 

[Pessimistic]

Looking back on a sample of 30 years its amazing how a club sticks to its own side of the 1:1 diagonal when it rises up into contention

Swans eagles dockers magpies crows bulldogs are almost invariably on the defensive side, over several premiership cycles
Hawks cats bombers invariably on or above the line..

Only the saints have appeared on bioth sides.

You have to say the long career of malthouse and the shorter one of ross lyon is in effect either.

Swans have over the period gone out to poach the best goalkickers. Capper plugger bazza tippett buddy. Its almost a waste of the afls resources

 

[The King!]

Looking back on a sample of 30 years its amazing how a club sticks to its own side of the 1:1 diagonal when it rises up into contention

Swans eagles dockers magpies crows bulldogs are almost invariably on the defensive side, over several premiership cycles
Hawks cats bombers invariably on or above the line..

Only the saints have appeared on bioth sides.

You have to say the long career of malthouse and the shorter one of ross lyon is in effect either.

Swans have over the period gone out to poach the best goalkickers. Capper plugger bazza tippett buddy. Its almost a waste of the afls resources

It is odd on your last point

2005 had hall oloughlin davis okeefe and goodes forward and were lower scoring than the spoon side makes no sense

But also we didnt poach capper

 

[AlibiMonday]

Final Siren can I ask do you have any way to provide a value of what a team needs to score to improve their predicted win tally for the rest of the season season, accounting for the lost "decimal" wins for the current game? For example, Fremantle are predicted to beat North 98-70 and North are expected to gain 0.2 wins for the purposes of the ladder predictor. If that is the exact margin of the game, North's position on the squiggle won't change, but they'll "lose" the 0.2 wins and therefore drop 0.2 wins on the ladder predictor. Therefore is it possible to provide get a figure or calculation of what North would need to score (as a % of Freo's score because that's how the squiggle works) to improve their total predicted wins because of an improved squiggle for the rest of the season even accounting for the lost "decimal" wins so to speak. If North were to lose by 1 point, they might lose the 0.2 wins, but with the improved squiggle position, they'd gain the .2 back over the remaining 14 games of the season, plus some more wins and improve their overall ladder position despite the loss. It's an "equilibrium" figure so to speak, and it'll be obviously more dramatic as the season goes on. It also won't work for all games, like GWS being predicted to beat Adelaide by three points and getting 0.55 wins. I don't think Adelaide will make up the "loss" of 0.45 wins by an improved squiggle position by only losing by 1 or 2 points and doing better than the squiggle prediction by only 1 or 2 points.

It might cost you a carriage return.

 

[telsor]

It might cost you a carriage return.

Don't forget the line feed!

 

[mad_eagle]

I'll do a lap of Subiaco nude before our home final if we finish in the top four.

We're in some good form right now, but we're just one or two injuries away from having to play guys who either don't deserve to or aren't ready to play AFL Footy. If you want proof just look at East Perth's results over the last few weeks.

We don't have the depth of a top four team

 

[cryptor]

I'll do a lap of Subiaco nude before our home final if we finish in the top four.

We're in some good form right now, but we're just one or two injuries away from having to play guys who either don't deserve to or aren't ready to play AFL Footy. If you want proof just look at East Perth's results over the last few weeks.

We don't have the depth of a top four team

I'm surprised you've kept teams to such low scores. I was under the impression your KPD stocks were completely smashed?

 

[mad_eagle]

I'm surprised you've kept teams to such low scores. I was under the impression your KPD stocks were completely smashed?

They are indeed. We've been able to hold it together so far, but if Gov or Schoey go down, the next guy in is a 19 yo kid by the name of Tom Barrass. He has talent and can clunk a mark, but he needs a full year in the WAFL before being thrown to the Sharks.

 

[Final Siren]

Final Siren can I ask do you have any way to provide a value of what a team needs to score to improve their predicted win tally for the rest of the season season, accounting for the lost "decimal" wins for the current game? For example, Fremantle are predicted to beat North 98-70 and North are expected to gain 0.2 wins for the purposes of the ladder predictor. If that is the exact margin of the game, North's position on the squiggle won't change, but they'll "lose" the 0.2 wins and therefore drop 0.2 wins on the ladder predictor. Therefore is it possible to provide get a figure or calculation of what North would need to score (as a % of Freo's score because that's how the squiggle works) to improve their total predicted wins because of an improved squiggle for the rest of the season even accounting for the lost "decimal" wins so to speak. If North were to lose by 1 point, they might lose the 0.2 wins, but with the improved squiggle position, they'd gain the .2 back over the remaining 14 games of the season, plus some more wins and improve their overall ladder position despite the loss. It's an "equilibrium" figure so to speak, and it'll be obviously more dramatic as the season goes on. It also won't work for all games, like GWS being predicted to beat Adelaide by three points and getting 0.55 wins. I don't think Adelaide will make up the "loss" of 0.45 wins by an improved squiggle position by only losing by 1 or 2 points and doing better than the squiggle prediction by only 1 or 2 points.

It's not practical to do that, since there's another factor that changes at the same time: the strength of the teams North Melbourne have yet to play. As other matches take place and clubs perform better or worse than expected, this will affect North's chances of beating them.

For example, North have no more games against Hawthorn, so they don't care what the Hawks get up to from now on. But if Collingwood have a shocker this weekend to Gold Coast, North's predicted wins will rise a little, since they meet in Round 9.

 

[Final Siren]

I'll do a lap of Subiaco nude before our home final if we finish in the top four.

bookmarked

 

[The Swans Blog]

It is odd on your last point

2005 had hall oloughlin davis okeefe and goodes forward and were lower scoring than the spoon side makes no sense

But also we didnt poach capper

Pess and clogged usually post some of the most biased, nonsensical crap, that you'll ever read on the main board.

 

[The King!]

Pess and clogged usually post some of the most biased, nonsensical crap, that you'll ever read on the main board.

thought he had a point i chose to ignore the poaching and afl resources crap and focus on the bit between the drivel

 

[The Falcon Strike]

I'm surprised you've kept teams to such low scores. I was under the impression your KPD stocks were completely smashed?

3 of our 4 best KPD were missing last week - so I would consider that smashed.

We have had Brad Sheppard taking on the likes of Schultz/Westhoff, Mccarthy, etc. It has worked so far - but at some stage someone like Jesse White, Jarrad Waite or Sam Reid is going to take hold of him.

 

[Lensen]

probably won't be jesse white

 

[threenewpadlocks]

It's not practical to do that, since there's another factor that changes at the same time: the strength of the teams North Melbourne have yet to play. As other matches take place and clubs perform better or worse than expected, this will affect North's chances of beating them.

For example, North have no more games against Hawthorn, so they don't care what the Hawks get up to from now on. But if Collingwood have a shocker this weekend to Gold Coast, North's predicted wins will rise a little, since they meet in Round 9.

How about what I suggested with the assumption that all other matches are played out according to the squiggle?

 

[Final Siren]

How accurate has the ladder predictor been in the first 10 rounds of a season in comparison to the final standings over past years?

Okay I did graphs. Everyone likes graphs.

These show the difference between the squiggle ladder predictor and the actual ladder at the end of the home & away season, as measured in average rungs difference per team, for 2010-2014.

So for example "2.0" here means the average team was predicted to finish two ladder rungs differently to where it actually did.

For comparison, the AFL ladder after each round is also charted. It starts a little later than the squiggle since there's no ladder before Round 1.

I did this in kind of a hurry but I think it's right.

 

[cryptor]

So my interpretation of those graphs is the Squiggle ladder is better to go off until about round 16 at which point there isn't much difference between it and the real thing.

 

[kaiserchief13]

So my interpretation of those graphs is the Squiggle ladder is better to go off until about round 16 at which point there isn't much difference between it and the real thing.

Considering it factors each team that's pretty bloody close each round and year.

 

[Jootube]

Squiggle has Freo beating West Coast by a point in the prelim.
Footyforcaster has West Coast beating Freo by a point...

disgonbegood.jpg

 

[Danger Zone]

[Edit! 2015 squiggles start here. Interactive squiggle (with tips, predictor & FAQ) is here. 2014 squiggles started here.]

I like to chart things for no good reason, so I decided to make a scatterplot of teams from their scores for and against over the course of the 2013 season. It looks like this:

After Round 18​

Each team's flag represents its current position, with the line tracking their journey since Round 1.

I added premiers from the last 20 years, too, since they mostly wind up in the same area.

The middle is an unreadable mess, but there are interesting results, too.

Sydney is currently sitting right where they were when they won the Cup last year. Hawthorn has tracked in a very small area all year, with an exceptionally strong attack but a weaker defense than any premiership-winning team of the last two decades. Geelong is making a late run. Freo look exactly like a Ross Lyon team.

There's a bunch of teams all around the same area, then a fairly large gap to Port Adelaide, Brisbane, St. Kilda, Gold Coast, and the Western Bulldogs. Then GWS and Melbourne sit a long way behind.

I also decided to plot the Top 4 teams of the last 20 years who failed to win the premiership and see where they wound up. So in this bunch we have many strong teams. I was interested in seeing whether there was a noticeable difference between flag winners and their closest competition:
​

Premiers vs Top 4 Also-Rans​

And there does seem to be. In fact, it's possible to draw a "premiership curve" that encompasses 13 of the 20 flags, and 75% of the time over the last 20 years, the team closest to or farthest beyond that curve has won the flag. (The five exceptions: according to this theory, Hawthorn should have won in 2012, Geelong should have won in 2008, St Kilda should have won in 2005, Brisbane should have won in 1999, and St Kilda should have won in 1997.)

Model Stuff: Each data point is calculated by taking a team's offensive rating and dividing it by the other team's defensive rating. For example, in a match between Hawthorn (OFF: 74.23%) and Essendon (DEF: 54.55%), Hawthorn is expected to produce a score 1.36 times higher than average. Each data point is a weighted average, representing 9% of the most recent round, 8.1% of the round before that (91% of 9%), then 7.45%, and so on. Aside from scores for and against, the only adjustment the model makes is for interstate games, where it assumes a 12-point advantage to the home team. This model has correctly tipped 117 winners this year (72.2%).​

Update! Play with Dynamic Squiggles here.

Shouldn't Adelaide have won in 2005, not St Kilda?

Sorry if this was already answered, so many pages.
Love the data by the way!

 

[clogged]

So my interpretation of those graphs is the Squiggle ladder is better to go off until about round 16 at which point there isn't much difference between it and the real thing.

I think what it says is that the Squiggle isn't really a better predictor of end of season placings that the actual ladder in any given round aside from the very early ones, even though it attempts to control for things like easy or difficult draw. At round seven, for example, Squiggle is on average only 0.5 placings more accurate than the ladder in round 7. And neither are very accurate, they're both off by around 2 placings.

So you could argue that the final ladder is probably going to end up as a compromise between Squiggle and the current ladder. Which means despite Squiggle saying they'll finish second, Hawthorn are not an unlikely chance of missing top four, and while Squiggle thinks Port will finish in the eight "Round 7 ladder" says they'll miss finals by fair way.