Certified Legendary Thread Squiggle 2017

[deflated]

Okay, the Swans season got me thinking. What is the highest number of consecutive weeks that a team has moved closer to (0,0) on the graph? It looks like every team except the Swans have impressed the Squiggle at least once so far, while Sydney continue their slow, uninterrupted descent.

 

[Del165198]

Okay, the Swans season got me thinking. What is the highest number of consecutive weeks that a team has moved closer to (0,0) on the graph? It looks like every team except the Swans have impressed the Squiggle at least once so far, while Sydney continue their slow, uninterrupted descent.

Im expecting some dramatic squiggling if you go down to the lions

 

[WhiskeyTangoFoxtrot]

Im expecting some dramatic squiggling if you go down to the lions

The Swans don't even need to lose to the Lions to go down in the Squiggle.

The Squiggle has them beating Brisbane 139-63 this week. So even a 10 goal win will see them heading downwards (or leftwards or both).

I'm happy to see the Squiggle is kind to the Crows this week, with only a 115-89 win required to keep their current position. Obviously it's easy to get ahead of yourself, but if the Crows maintain their season averages this week they should move up a bit, as well as slightly to the right.

 

[Final Siren]

Round 7, 2017​

Lots of validation this week for the squiggle theory that teams don't suddenly get a lot better or worse very often, with Richmond, Fremantle, and Essendon looking more like their owners put them up on blocks and spent the summer tinkering with the engine, rather than going out and buying a new car.

But not Sydney! Sydney are the strange one: a team that looked like a sports car throughout 2016 but then seem to have traded in for my old "fire engine red" 1978 Gemini.

The 2017 Sydney Swans​

Animated squiggling:

The Hawks crashed again, but the only surprise there was how bad it was; we knew they were wobbling toward the middle of the road with the bumper hanging off, but we didn't know there was a tram coming the other way. A number 96 tram, bound for St Kilda, this week.

But it was all good for Adelaide, who cruised past the Tigers while Geelong lost to the Pies and GWS barely outlasted the Bulldogs.

The Bulldogs currently look locked in a battle for a Top 4 spot with Port Adelaide, who also had a good week. In fact, the Power may well have a real vehicle here, as they haven't had a bad squiggle all year, so could wind up leaving the Cats and Dogs to fight for 4th. But for now, it's looking like this:

Or in animated form:

Tons of uncertainty through the middle, with many teams capable of finishing all over the place.

It's worth noting how bad Brisbane are. They were terrible late last year and have been consistently terrible all this year. I keep hearing talk about how improved they are and I don't get it. Only a handful of teams in the last 10 years have had a sub-40 Defence rating in the squiggle, including the expansion clubs, and Brisbane is just camping out there. It's pretty hard to find wins when you can't stop the opposition from scoring.

And for all the talk of the Tigers' new attacking game style, they're still a defensive team. A couple of games in the wet haven't helped, but there isn't much evidence that they can score well against good opposition.

So after 6 rounds we have:

• Teams with improved 2017 models: Port Adelaide, Richmond, Adelaide, Gold Coast, Essendon, Fremantle, St Kilda (only because of their last game), Geelong (being generous).
  
  
• Teams still driving their 2016 models: Brisbane, West Coast, GWS, Collingwood, North Melbourne, Melbourne, Carlton, Western Bulldogs (being generous).
  
  
• Teams still driving their 2016 models and there's this weird noise whenever you brake that you should have had checked out months ago and now there's smoke coming out: Hawthorn, Sydney.

Flagpole! Squiggle hasn't rated the Tigers like their 5-0 start would suggest, but the Crows' 76-point win was still enough for yet another week of "yay Adelaide."

There was a question earlier about how Sydney can rated so highly when they face a challenge to even make finals. And the answer is yes, this is more or less an "if they make finals, how will they go" rating. More specifically, it's an algorithm that survived a deathmatch against tens of thousands of other algorithms in a competition to rank the eventual premier highly during the season. It hasn't been trained to care about teams lower down the pecking order, so long as they're not bumping out the eventual premier. And it's completely ignorant of how likely the team is to make finals and whether they get home games or double chances if/when they get there.

I can probably improve this now that squiggle is actually running season simulations, but for the moment, it's a "premiership form" rating, where it rates highly teams who are most delivering results similar to those of premiers from the last 20 or 30 years.

Live squiggles!

Squiggle dials!

 

[Crom]

Love your work as always

 

[WhiskeyTangoFoxtrot]

Final Siren, how does the Squiggle deal with the earlier games of a team that drastically changes form over the season?

For example, Port beat Sydney in R1 and both teams had a big Squiggle movement from that game. As the season has gone on it appears that both Port and Sydney were mis-judged. Port are much better than the Squiggle expected and Sydney much worse.

So does that R1 movement get moderated as the year goes on or does it stay the same?

 

[chazwazza]

Hawthorn and Sydney in a sprint to the death zone

 

[Final Siren]

Final Siren, how does the Squiggle deal with the earlier games of a team that drastically changes form over the season?

For example, Port beat Sydney in R1 and both teams had a big Squiggle movement from that game. As the season has gone on it appears that both Port and Sydney were mis-judged. Port are much better than the Squiggle expected and Sydney much worse.

So does that R1 movement get moderated as the year goes on or does it stay the same?

It stays the same. The model you describe is a "two-pass squiggle," so it plays the season out like normal, then goes back and re-evaluates the results using the new team positions.

I've tried that, but haven't tested it rigorously to see how it does over time. I should probably do that instead of spending time thinking up car analogies. But the 2-pass chart currently looks something like this:

​

One disadvantage of the 2-pass model is that squiggle lines shift retrospectively. So you can have a R1 result where you zoom upward, and a week later it's been revised back because the R2 results of the team you beat make your win over them no longer so impressive.

 

[vide0n]

It stays the same. The model you describe is a "two-pass squiggle," so it plays the season out like normal, then goes back and re-evaluates the results using the new team positions.

I've tried that, but haven't tested it rigorously to see how it does over time. I should probably do that instead of spending time thinking up car analogies. But the 2-pass chart currently looks something like this:

​

One disadvantage of the 2-pass model is that squiggle lines shift retrospectively. So you can have a R1 result where you zoom upward, and a week later it's been revised back because the R2 results of the team you beat make your win over them no longer so impressive.

I like how the squiggles of other teams make North look like it's sitting in a singularity

 

[WhiskeyTangoFoxtrot]

It stays the same. The model you describe is a "two-pass squiggle," so it plays the season out like normal, then goes back and re-evaluates the results using the new team positions.

I've tried that, but haven't tested it rigorously to see how it does over time. I should probably do that instead of spending time thinking up car analogies. But the 2-pass chart currently looks something like this:

​

One disadvantage of the 2-pass model is that squiggle lines shift retrospectively. So you can have a R1 result where you zoom upward, and a week later it's been revised back because the R2 results of the team you beat make your win over them no longer so impressive.

Cheers for that. Very interesting.

I'm used to dealing with ABS data which gets revised over 7 time periods, sometimes even resulting in a positive result ending up being adjusted to be a negative result over a year later once future data points are established.

It looks like Port actually benefited the most from the re-jig as, even though Sydney have gotten worse, Fremantle, Adelaide, GWS and Carlton all improved after Port played them.

 

[WhiskeyTangoFoxtrot]

I like how the squiggles of other teams make North look like it's sitting in a singularity

North have probably moved the least out of all the teams except Brisbane. Lots of close losses largely in-line with what Squiggle projected.

 

[LeverPuller]

Squiggle only predicting a 3pt Melbourne win, time for a Squiggle boost!

 

[Andre]

Final Siren you've done in the past a squiggle where everyone starts at the centre, only taking that years results into account. Are you able to do that? 6
Rounds in we're a quarter of the way through the season, Id be interested to see the what changes occur if it's a 'clean slate' minus the 2016 results still having an effect.

 

[Final Siren]

Final Siren you've done in the past a squiggle where everyone starts at the centre, only taking that years results into account. Are you able to do that? 6
Rounds in we're a quarter of the way through the season, Id be interested to see the what changes occur if it's a 'clean slate' minus the 2016 results still having an effect.

Andre's Explosive Squiggle!

This is if all teams start the year at 50/50, so ignoring all results before this year.

​

e: For some reason it's not plotting the line from 50/50 to where each team is at after R1 results. But imagine that's there.

 

[deflated]

Final Siren, how does the Squiggle deal with the earlier games of a team that drastically changes form over the season?

For example, Port beat Sydney in R1 and both teams had a big Squiggle movement from that game. As the season has gone on it appears that both Port and Sydney were mis-judged. Port are much better than the Squiggle expected and Sydney much worse.

So does that R1 movement get moderated as the year goes on or does it stay the same?

Would you really want to moderate that R1 movement? The magnitude shows that at that time it was a very unexpected result which is still useful information.

I'm also not sure that squiggle positions now are any more representative of each team's true R1 position than the squiggle starting point. The Swans appear to be appreciably worse now than they were a month ago (the mob that wilted against Carlton wouldn't be coming back to lead in the 4th against the Dogs). Injuries happen. As the season plays out the squiggle adjusts; the squiggle knows what its doing.

 

[Hobbes]

Final Siren, how does the Squiggle deal with the earlier games of a team that drastically changes form over the season?

For example, Port beat Sydney in R1 and both teams had a big Squiggle movement from that game. As the season has gone on it appears that both Port and Sydney were mis-judged. Port are much better than the Squiggle expected and Sydney much worse.

So does that R1 movement get moderated as the year goes on or does it stay the same?

My algorithm rates your past results against the current rating of the opponent. So, I think it can do a good job in the event of a massive form shift. Like the squiggle it liked Sydney at the beginning of the year, but because I place more stock in recent results (last 13 rounds, but two thirds of my ratings come from the last five rounds), Sydney's fall has been quicker.

 

[BEaston]

This is if all teams start the year at 50/50, so ignoring all results before this year.

​

Hey mate, any chance of including the 2-pass and explosive images each week in your weekly update? Only if it's not a hassle and you actually want to of course. Just think it could be cool to compare the models each week.​

 

[cryptor]

Andre's Explosive Squiggle!

This is if all teams start the year at 50/50, so ignoring all results before this year.

​

e: For some reason it's not plotting the line from 50/50 to where each team is at after R1 results. But imagine that's there.

Hawthorn the clear worst performer. As expected.

 

[cryptor]

Hawthorn and Sydney in a sprint to the death zone

Maybe there's something good there we're not telling the rest of the comp about...? Race ya!

 

[Andre]

Andre's Explosive Squiggle!

This is if all teams start the year at 50/50, so ignoring all results before this year.

​

e: For some reason it's not plotting the line from 50/50 to where each team is at after R1 results. But imagine that's there.

Excellent. Thanks for that. Obviously as the season goes on, this and the usual squiggle will get closer, but as per fpcookie , if for now whilst they are so far apart, if we could see the 2017 only one as well after each game it'd be great.

 

[Soren Lorenson]

Maybe there's something good there we're not telling the rest of the comp about...? Race ya!

The Lions have had a really good look over an extended period of time and there is nothing particularly great I can assure you.

 

[chazwazza]

Andre's Explosive Squiggle!

This is if all teams start the year at 50/50, so ignoring all results before this year.

​

e: For some reason it's not plotting the line from 50/50 to where each team is at after R1 results. But imagine that's there.

Adelaide in The Honeymooners "TO THE MOON ALICE!!!" mode

 

[chazwazza]

Maybe there's something good there we're not telling the rest of the comp about...? Race ya!

I tell you what, you go down first and make sure it's safe, I'll wait back here and guard the entrance and call for help if anything happens.

 

[#1_pigeonracer]

Interesting read this week Max and great to see all the movement. I noted you mentioned St Kilda's state is really only as a result of the Hawthorn take down. In a similar vein, media leading up to last weekend was only about the few wins we had with no mention of being 'in' games (matching) Cats and WC until the 4th quarter. Class and running out of gas getting us easily both times. Is there any modelling which looks beyond the final siren score?

 

[Gavin Excell]

Interesting read this week Max and great to see all the movement. I noted you mentioned St Kilda's state is really only as a result of the Hawthorn take down. In a similar vein, media leading up to last weekend was only about the few wins we had with no mention of being 'in' games (matching) Cats and WC until the 4th quarter. Class and running out of gas getting us easily both times. Is there any modelling which looks beyond the final siren score?

Isnt that reflected in %?