Analysis Amateur graphical look at interstate v vic games

[Swanks McSwankserton]

So basically what you are saying is that Victorian bias is pretty much comprehensive except against West Coast, just one "interstate" side, who have been able to somewhat bring the ledger closer to the middle. 1 club, by becoming the biggest, richest and most supported club in the land have been able to go against the grain an combat blatant Victorian Biases.

Some outcome of Statistical Hypothesis Test: Victorian Bias is all pervasive and Statistically real, but becoming bigger, richer more supported than any other club in the League gives you a statistically better chance of combatting that Bias.

I think you're referring to this line:

Interstate sides as a group have as many premierships you'd expect them to, but west coast is carrying some members.

which I was using to summarise this:

Also worth noting that although the group is on track so far, individually it's more whacky. A year is a crazy long time, and with 18 teams each side is expected to lose a grand final, win 1 premiership than go into an immediate 16 year grand final draught before repeating again. So while Adelaide have a 22 year premiership drought so far (second longest of an interstate side after Freo), they're still about 3 years ahead of their expected premiership schedule, which means they've only just passed the halfway mark of their expected premiership drought (assuming the AFL doesn't add any more teams in the next 20 years, which would extend it). Meanwhile of all things Gold Coast is considered the second most hard done by interstate team on expected premierships (after Freo). Port then are the least hard done by of the sides in the -ve, depite having a premiership drought 7 years older than Gold Coast has been a thing.

and my thoughts on the stats in the graph on expected v actual premierships for group v individual,

so my apologies for that. What I was getting at was more similar to what Ambrose was saying in his last post. As a group expected premierships line up, but individually they're skewed towards some clubs (the big ones it looks like, in a self fulfilling feedback loop probably), not that west coast's stats are hiding vicbias. This is the last graph again but I fliped who was victorian and who was interstate:

and while I couldn't be bothered to fix the sucky colouring (a devilspawn hybrid of the prelim project and this one), you can see how this would support the statement: 'Victorian sides as a group have as many premierships as you'd expect them to, but Hawthorn is carrying some members.'
There are only four sides more than 0.6 premierships down on their expected premierships and that's -2.52 St kilda & Melbourne, -1.56 Fremantle, -1.52 Bulldogs (Fitzroy excluded as occupying a weird limbo in this discussion). There's only three sides more than a premiership up on expected and that's +6.48 Hawthorn, +1.89 Eagles, +1.48 Essendon

Without doing the math, you could expect the variance in both cases to just be random streaks though (like one person flipping four heads in a row and another four tails still being the expected results from 8 coin flips, even if it is an unlikelier sequence), we just don't have enough data to know anything about anything.



p.s. ik people probably want a graph of victorian clubs starting at 1897 but my program is really not meant to handle 0 interstate v vic games a year, or to skip collecting data from games, so someone else's turn please

edit: changed 'changed' to flipped and '1987' to '1897'

 

[WestCoast05]

...

Despite the West Coast / Richmond trolling that immediately followed thanks for all the hard work you put into this!!

 

[Ambrose Burnside]

so my apologies for that. What I was getting at was more similar to what Ambrose was saying in his last post.

Aw shucks

 

[Dr Tigris]

I think you're referring to this line:

which I was using to summarise this:

and my thoughts on the stats in the graph on expected v actual premierships for group v individual,

so my apologies for that. What I was getting at was more similar to what Ambrose was saying in his last post. As a group expected premierships line up, but individually they're skewed towards some clubs (the big ones it looks like, in a self fulfilling feedback loop probably), not that west coast's stats are hiding vicbias. This is the last graph again but I fliped who was victorian and who was interstate:
View attachment 1065370
and while I couldn't be bothered to fix the sucky colouring (a devilspawn hybrid of the prelim project and this one), you can see how this would support the statement: 'Victorian sides as a group have as many premierships as you'd expect them to, but Hawthorn is carrying some members.'
There are only four sides more than 0.6 premierships down on their expected premierships and that's -2.52 St kilda & Melbourne, -1.56 Fremantle, -1.52 Bulldogs (Fitzroy excluded as occupying a weird limbo in this discussion). There's only three sides more than a premiership up on expected and that's +6.48 Hawthorn, +1.89 Eagles, +1.48 Essendon

Without doing the math, you could expect the variance in both cases to just be random streaks though (like one person flipping four heads in a row and another four tails still being the expected results from 8 coin flips, even if it is an unlikelier sequence), we just don't have enough data to know anything about anything.



p.s. ik people probably want a graph of victorian clubs starting at 1897 but my program is really not meant to handle 0 interstate v vic games a year, or to skip collecting data from games, so someone else's turn please

edit: changed 'changed' to flipped and '1987' to '1897'

So you're saying that the clubs with the most resources win more often than those with less resources!!!

And that is independent of state!!!!!

Actually great analysis thanks. So we end up with something fairly predictable, but interesting. No significant state bias. But a relatively strong bias towards $ and good management. WCE and Hawks being well run and good financially over a long time = success. Hope that works for the Tigers now. More premierships would be good.