I Blame the Eagles

Not a great weekend for most Investors, due largely, I'd contend, to the waywardness of the Eagles, whose 9.20 was insufficient to prevail over the Dockers' 7-fewer-scoring-shot 13.9. Put simply, the Eagles should have won. (Okay, okay ... perhaps the Hawks were a little lucky to win, but surely I'm as entitled as the next person to attribute good luck to superior foresight and bad luck to ... well, sheer bad luck.)

Most Investors suffered losses in the 1.5% to 2% range, though MIN#002 fared worst, losing 7.88% and MIN#017 fared far better, gaining 6.39%. The good news is that all Investors have made a profit so far this season.

On tipping, ELO had an extraordinary weekend, bagging 7 from 8, taking it to joint-leadership on 30 from 48, level with BKB (it was only a matter of time, wasn't it?), STM II, Shadow and Silhouette. Only 4 tips separate 1st from last now, with Chi, HSH, EI I and EI II filling the bottom places on 26 from 48.

In stark contrast with its tipping performance, ELO managed just 3 from 8 on line betting, moving it to 26 from 48 for the season. Chi. meantime, has recorded just 21 from 48 on line betting, meaning that betting against him would have been profitable whereas betting with him would not. Hmmm ... good thing he only bets head-to-head then.

** Please note that entries in the Pick the Ladder Competition are due by midnight this Wednesday. **

And Now The Contest Begins

This weekend, for Investors, everything changes. All Funds are now active and, as it happens, all Funds are active. New Heritage has four bets; Prudence has three; Chi-squared, Hope and Line Redux have two each. Only two games are wager-free - Port v Adelaide and Melbourne v Geelong - the first because Chi eventually opted for Port rather than Adelaide by 1 point, and the second because not even a MAFL Fund could hold its nose long enough to wager on the Dees at $11 up against the Cats.

In aggregate, a little over 15% of funds are in play for those with the Recommended portfolio.

West Coast and Brisbane, in particular, will carry the hopes of those with the Recommended portfolio. To a lesser extent, so too will Sydney and Hawthorn, the Roos and the Bulldogs.

Before I move on from wagering considerations I feel duty-bound to note that the Dees have now moved to $13 and the Cats to $1.01. In terms of the data I have, no team has ever previously been as slender-chanced as the Dees. Even at the original offer of $11, imagine what the Heritage Fund would have thrown at the Dees this weekend had this Fund still been active. (For old times' sake - whatever that means - I ran the Heritage Fund algorithm on the current round. It would have wagered almost 15% on the Dees as well as 7% on the Roos and 2% on the Bulldogs. I don't really miss the Heritage Fund.)

On the line market the Dees are only being given 58.5 start, which I think is a tad underdone when you consider that they received 75.5 points start last year in Round 3 when they were away to the Cats and at $12 and, more relevantly, 60.5 start in Round 19 when they were at home to the Cats and priced at just $10.

On tipping:

• Collingwood are favoured 12-1 over the Roos, and only Home Sweet Home is opting for the Roos. That said, both ELO and Chi have the Pies as only 2 point favourites, in ELO's case making this its Game of the Round.
• Carlton are 11-2 favourites over last year's premiers, Hawthorn. BKB is opting for Carlton because, with the Blues and the Hawks equal favourites at noon on Wednesday, BKB aligns itself with CTL's Carlton tip. (A couple of weeks back, when Freo and Adelaide were equal favourites, I forgot to apply this tie-breaking rule for BKB. I've since corrected this, giving BKB an Adelaide tip for this game - as it turned out, a correct tip.)
• West Coast are 8-5 favourites over Freo. All of our top 5 tipsters except STM II are with the Eagles.
• Essendon are 9-4 favourites over the Lions. BKB is the only top 5 tipster opting for the Lions.
• Port Adelaide are 7-6 favourites over Adelaide. Chi has vacillated over this game all week, swapping between Port by 1 point (with a 10%+ wager) and Adelaide by the same margin (but without a bet). Despite not having a wager (perhaps because of it), Chi has this as his Game of the Round. Amongst the top 5 tipsters only Silhouette is tipping Adelaide.
• Sydney are 8-5 favourites over Richmond. Amongst the top 5 tipsters only STM II is tipping Richmond.
• Geelong are 12-1 favourites over Melbourne. Once again, only Home Sweet Home feels compelled to support the underdog.
• St Kilda are 12-1 favourites over the Dogs, where, yet again, it's HSH that's out on its own.

On line betting, Chi's with the Roos, Carlton, West Coast, Essendon, Adelaide, Richmond, Melbourne and the Dogs; ELO's with the Roos, Hawthorn, West Coast, Essendon, Port Adelaide, Sydney, Melbourne and the Dogs.

Good Wagering, Hard Tipping

It'd be churlish to be disappointed about our wagering performance this weekend though it was only a stray goal from the Hawks that stood between our actual 3-2 performance and a far more impressive 4-1. Speaking of stray, the other losing bet was the Dogs, but no amount of alternative futuring could readily turn their performance into a victorious one.

So we finish the weekend with no Investor in the red and all but MIN#017 comfortably in the green.

Though we made money on the Funds' implicit tips, it was a tough weekend for our official tipsters, with 5 favourites losing. Our best tipsters - Silhouette, ELO and Home Sweet Home - managed just 4 from 8. (This week please note that I've added another column to the tipster performance summary on the right. It's headed "Return" and reflects the return that would have been achieved from a 1 unit wager on that tipster's tips.) 

Chi performed admirably on line betting, bagging 5 from 8, but this takes him to a no-better-than-chance 20 from 40 for the season. ELO slipped again, scoring just 3 from 8 this week, but remains profitable for the season with 23 from 40. (By the way, ELO has generally been profitable in seasons past if line wagers were placed only on those teams  predicted to win by 13.5 points or more after the handicap is taken into consideration. Following that strategy this year would have produced a 3.3 unit profit so far.)

If you're curious about the latest MARS Ratings, these are available on the MAFL Stats site. You'll see there that the 8 highest-ranked teams are, in order, Geelong, St Kilda, Hawthorn, Western Bulldogs, Collingwood, Sydney, Adelaide and Carlton. Six of these teams are also in the top 8 of the competition ladder (which, by the way is also available on the MAFL-Stats site), the two differences being the inclusion of the Hawks and the Swans in the MARS Top 8 at the expense of Port Adelaide and Essendon.

We Now Have Hope

This week we ratchet up another level as the Hope Fund comes on stream and starts out with a couple of bold bets - 5.42% on Essendon @ $2.90 and 4.6% on the friendless Freo @ $2.25 - and one apparently safer bet of 2.59% on the Dogs @ $1.68.

The Line Redux Fund adds two more games to the list of those in which Investors have a financial interest by lobbing 5% at Hawthorn giving 22.5 start to West Coast, and another 5% at Geelong giving 38.5 start to Brisbane.

In total then, much as I'd foreshadowed on the site earlier in the week, we've about 12.6% of the Hope Fund and 10% of the Line Redux Fund at risk.

On tipping, the favourites are more heavily supported by our tipsters in just five of the eight matches. The details are as follows:

• St Kilda are favoured over Port Adelaide 10-3. ELO is tipping the Saints by just 2 points making this its Game of the Round.
• Collingwood are favoured over Essendon 8-5, though Chi and ELO are tipping only about a 1 goal margin.
• West Coast are favoured over Hawthorn 9-4 despite heavy Hawk victories being predicted by BKB, ELO and Chi.
• The Roos are favoured 13-0 over Richmond.
• Sydney are favoured 12-1 over Fremantle though Chi predicts the Swans by just 3 points making this his Game of the Round.
• Geelong are favoured 12-1 over the Lions, Easily Impressed II being the sole Lions adherent, a consequence of its successfully tipping them last weekend.
• The Bulldogs are favoured 12-1 over Carlton. In this game it's Easily Impressed I that's the outlier, here because Carlton won and the Dogs lost last weekend.
• Melbourne are favoured 7-6  over Adelaide.

Chi bagged 5 from 8 on line betting last weekend to take him to just 15 from 32 from the season. ELO managed just 4 from 8 but remains at a healthy 20 from 32 for the season. Chi's and ELO's Mean Absolute Prediction Errors reflect this difference in line betting performance: Chi's on 34.6 points per game and ELO's on 31.3 points per game, just 0.8 points behind BKB.

Chi's Line Bets are: Port Adelaide (probably - we've no market yet), Essendon, West Coast, Richmond, Fremantle, Brisbane Lions, Western Bulldogs and Melbourne.

ELO's Line Bets are: St Kilda (again, probably), Essendon, Hawthorn, Kangaroos, Sydney, Brisbane Lions, Western Bulldogs and Melbourne.

Pick the Teams' Finishing Order Competition

A while back I mentioned that we'd be running a competition this year in which the aim will be to predict the finishing order of all 16 teams. The winner will be the person whose predictions are closest to the actual ladder positions at the end of the home and away season.

Here are the logistics of the competition:

• Entry is free. (I was considering charging a nominal entry fee and using this to create a prize pool but I thought a free competition would encourage higher levels of participation.)
• To be eligible, entries must be received by me by midnight on Wednesday, May 6th. That means you'll be able to use the ladder as at the end of Round 6 as the basis for your predictions.
• An entry comprises a finishing order for all 16 AFL teams.
• Only one entry is allowed per person.
• Order will be determined by the Kendall's tau measure as described below.
• The final ladder positions for the teams will be those published on the www.afl.com.au site at the end of the home and away season.
• The prize? You'll gain the people's ovation and fame forever (with apologies to Iron Chef).

Okay, so that's the logistics. Now for some detail. (You can safely skip the remainder of this blog if you're not interested in how we'll decide on a winner.)

To judge the winner we need a measure of proximity for two rankings so that we can compare each entrant's predicted ranking with the ranking provided by the competition ladder. The statistical community has a number of such measures in its armoury, one of which is called Kendall's tau and this is the measure that I'll be using to determine whose predictions are closest to the final ladder.

Kendall's tau is based upon the notions of concordance and discordance. Imagine that, in my predictions, I've placed Team A above Team B. Then, if the end of season ladder has Team A finishing above Team B (with any number of teams in between), my rankings of Team A and B are said to be concordant with the final ladder. If instead, Team B finishes ahead of Team A, my rankings of Team A and B are then said to be discordant with the final ladder.

Now imagine that I considered every possible pair of teams and I counted the number of concordances and discordances in my rankings compared to the final ladder. Kendall's tau is defined as the difference between the number of concordances and the number of discordances, divided by the total number of possible pairs of teams.

The closer is Kendall's tau to 1, the closer my predictions match the final ladder; the closer it is to 0, the more random my predictions are relative to the final ladder; and the closer it is to -1, the closer my predictions are to a reverse ordering of the final ladder, an outcome that would surely be far more embarrassing than registering a zero. The winner of our competition will be the person with the greatest Kendall's tau.

A small example might help to clarify all this. So, let's assume that there were only six teams in the competition, imaginatively named A through F. Then, say I predicted they'd finish B, F, D, A, C, E but that they instead - with a commendable sense of order - actually finished A, B, C, D, E, F. 

Now, there are 15 possible pairs of teams that we can consider, and my predictions are concordant with the actual finishing order for 8 of these pairs (A&C, A&E, B&C, B&D, B&E, B&F, C&E and D&E) and discordant for 7 of them (A&B, A&D, A&F, C&D, C&F, D&F and E&F). My Kendall's tau would therefore be (8-7)/15 or about 0.07, which is barely better than the chance score of 0.

Somebody else who predicted a finishing order of B, A, D, E, C, F would, instead, register a Kendall's tau of 0.6, having just 3 discordances and 12 concordances. I think it's fairly apparent that this latter ordering is far closer to the actual ordering than was mine.

One of the nice properties of Kendall's tau is that it has a probabilistic interpretation. If the Kendall's tau calculated for your predictions is K then the probability of concordance between your predictions and the ladder for any two randomly chosen teams is (K+1)/2. So, for the example just presented where K was 0.6 this probability would be 0.8, which could also be derived by noting that there were 12 concordances in the 15 possible pairings and 12/15 = 0.8.