Thursday, March 29, 2007

No casino!

For once I'm pleased with politics in the UK, and for the apparent conservativeness of Lords over MPs. The Lords have thrown out the government's proposals for a "super-casino" in Manchester - see here. It seems finally some airing is being given in the media to the rampant social problems that this kind of thing can (and I believe will) cause. We haven't heard much about them because the driving forces behind these casinos have a lot of money.

One example is research done in the States by a Christian economist*, showing that the social cost actually exceeds the social benefit. This is counter to most research, usually funded by the gambling promoters, which suggests that opening casinos would be great.

And sure enough, MPs and the Chamber of Commerce in Manchester are up in arms about the potential job losses. I find these arguments intolerable. Let's provide jobs to completely mess up our society, and let problem gambling increased! Why not publicly build a few other socially undesirable things too while we're at it.

There are plenty of more virtuous means of providing jobs. Crazy, really mind-boggling ideas like perhaps build loads of sporting facilities to kids can play sport much more often, rather than accompany their parents to the casino, and rather than eating yet more junk food on their ever faster march towards obesity. It'll never happen...

*Grinols, E. 2004, Gambling in America: costs and benefits, Cambridge, CUP

Labels: , , , ,

Saturday, March 17, 2007

Leyton Orient 2-2 Oldham Athletic

Well, I'm yet to see Latics lose this season, and while they came close to losing this match at Leyton Orient, falling two goals behind with twenty minutes to play, I am still slightly puzzled at how on earth Oldham didn't win this one at a canter.

Undoubtedly Latics were helped by Gary Alexander getting himself stupidly (and deservedly) sent off - first for dissent in the first half, and then a very late challenge on Haining. I've never understood football supporter logic - Haining was pole-axed by a terrible challenge, and Alexander deservedly sent off. Yet Haining still gets boo-ed by the Orient fans! What was his crime? Happening to be in the way of a horrific challenge from a clearly overheated player?

Goals were certainly to be expected in this match, and you could see why Orient have scored so many and conceded an awful lot too - they created chances going forward, but were wide open at the back.

Before the game was many minutes old, the pattern had been set, with Orient trying to attack, and doing so dangerously, but looking dodgy at the back. Then came a rather freakish goal by Orient, when a loose ball was chased down. Alexander, on the by-line, hit the ball hard across goal, and it must have caught in the wind, and perhaps he hit it with the outside of his boot, but one way or another, the ball hit the far post (I'm not convinced Alexander could see the far post!) and went in the net! Latics responded well, and Warne when given a clear chance forced a good save by the Orient keeper. Gregan headed over, and later in the half Warne hit a powerful shot which beat the keeper but rebounded off the bar.

The first half ended with Latics still a goal behind, and despite their chances, not playing particularly well. Orient had had very promising moments of their own, and could certainly have gone in at the break more than one goal to the good.

The second half began with a moment that changed the match; as already mentioned, Gary Alexander got himself sent off for a late and high challenge on Haining. There can be little doubt about the decision. This then set-up Latics to dominate proceedings. Rocastle hit the bar with a shot when in the clear, and easily the most controversial moment of the match followed soon after. More good football by the Latics, and a dangerous cross was headed towards goal. From my vantage point it had clearly crossed the line, and the Latics players also appeared to think so. Nevertheless, an Orient player had cleared it "off the line", and none of the officials saw anything. Another scramble a few moments later somehow saw the ball go over the bar when it should have gone in.

After all this pressure there then came another moment of madness at the back, as a long ball held up on the wind, and Latics keeper Pogliacomi misjudged it, leaving the Orient man Hooper with the task of lobbing the ball into the net, which he did well. At 2-0, the game looked up. However, Latics had fought back from two down earlier in the season against the same opposition, and immediately resumed their onslaught on the Orient goal. Not long afterwards, a far post cross looked like it had eluded everyone, but Taylor ran in from seemingly nowhere to nod the ball into the far corner of the goal, giving Latics hope at 2-1.

Having not scored in 51 Oldham matches, Taylor now has four goals in three games, and the goal rejuvinated the Latics. Clarke joined the club started by Paul Warne and Craig Rocastle by hitting the crossbar with a far post header, before on 81 minutes Warne hassled an Orient defender and won the ball off him, and in the ensuing scramble Richie Wellens won the ball only to be fouled by Brian Saah. Thankfully the referee pointed to the spot, and Liddell duly obliged with a cool penalty into the right hand corner of the net, just out of the reach of the keeper's outstretched arm.

Having fought back from two down, one would have expected Latics to have pushed for the winner, but in the match between these sides earlier in the season, Latics fell behind again after pulling back to 2-2. This didn't happen today, and Latics really ought to have gone on to win. No more woodwork hitting, but at least three important saves by the Orient keeper, the final one rebounding to Leon Clarke who thought finally he'd got the goal his performance deserved when he slotted home, only to see the linesman's flag contribute yet more to a frustrating afternoon for him and the Latics.

All in all, it was one of those matches, where somehow Oldham didn't win. Orient played their part, looking dangerous going forward, and battling fiercely throughout. Given the number of goals the their matches tend to attract, it'd be great to have them in the division again next season. Nevertheless, hitting the woodwork three times, having a goal ruled out, and another not seen by the officials (!), there can be little doubt Latics should have won. All the more frustrating were the 85th minute goals for both Bristol City and Nottingham Forest in other matches today. Latics are now a distant 8 points from 2nd spot, a position increasingly looking out of their grasp.

I always fancied the play-offs anyway...

Saturday, March 10, 2007

Back in prediction mode...

Without too much attention given, as my thesis has taken hold this last week, but running existing models on updated data to get new predictions, here are this week's predictions.

Tomorrow Oldham entertain Doncaster at home. We always lose to Doncaster, so I'm pessimistic. My attendance model suggests 5628, which doesn't seem a mile out. Oldham's form is shot, and 5 defeats in 6 home matches suggests the crowds won't be flocking. Doncaster I wouldn't have thought would bring too many supporters, though I could be surprised. They're on a good run, having won at Forest on Tuesday, and given Latics have picked up one point from the last 15, it's not looking overly positive. I don't know what effect having the game on Sunday will have. Given Latics have started playing more Sunday games recently, it might be worth throwing in a Sunday `dummy' to try and see if there is an effect, like there is with a Tuesday.

Turning to match score prediction, I've run my model additionally on all League One matches this weekend, most of which are 15 minutes old as I write. The model suggests the probabilities given in the caption below:

One of these has already come to fruition, as Huddersfield beat Bradford 2-0. Oldham are favourites against Doncaster, but I would add only because this model doesn't include form.
Nonetheless, comparison with Finktank shows that again I'm reasonably in line with their complicated models: they put Oldham's probability of winning at 43.4%, although they see a draw less likely at 27.3%, and Doncaster at 29.3%. I'd likely agree with theirs - a draw is less likely than a Doncaster win.
The following scores are most likely:

0-0 17.5%
1-0 18.0%
0-1 12.5%
1-1 12.9%
2-1 6.6%
1-2 4.6%
I'm not overly inclined to put too much weight on these, although having said that, I don't expect it to be a high scoring encounter tomorrow. Maybe I'll be confident, and go for a 1-0 win, a bit like those early season 1-0 wins over Scunthorpe and Swansea, which came when the team was shaky on confidence, as it likely it at the moment.
Come on Oldham!

Saturday, March 03, 2007

Predicting football match outcomes...

Well, it took long enough, as these things always do, but now I have a model that predicts football match outcomes. The predictions of the model I'll assess in the weeks to come if I get a moment, but I'm rushing towards a thesis submission in May, so time is getting tight.

Nevertheless, the predictions this model provides are very much in line with what the bookies think, and in line with the predictions of Finktank, the Dectech enterprise that publishes predictions on football matches each week in the Times. What is this model? It's a very simple model which describes the process determining the number of goals each team scores in a match as belonging to a Poisson distribution. The Poisson distribution matches incredibly well the arrival of goals in football matches, and so if X is home goals in a match, and Y is away goals, then both can be described as Poisson processes. It's likely of course that there's some interaction between these two processes, and in this case, a bivariate Poisson distribution of (X,Y) would be sough.

Making predictions on such bivariate models is a trivial extention of what I've done already, but I haven't the time to do that yet. Maybe in May. Once the season's finished...

Anyhow, in the meantime, what does the model predict?

Take the currently running Liverpool v Man U match. Finktank thought beforehand Liverpool had a 43.4% probability of winning, with the probability of a draw at 29% and a Man U win at 28%. The bookies favoured a Man U win over a draw, suggesting that Liverpool had a 36% chance of winning, the draw at 31% and the Man U win at 33%. The simple double Poisson model I've run (on all matches before today this season in the Premiership) suggests that Liverpool have a 37% chance of winning, the draw at 30% and Man U at 33%.

After 65 minutes, the match is locked at 0-0, and the first half was a very tight affair, reflecting these evenly matches odds. A contrast is given for the Arsenal v Reading match, which is a home banker if anyone ever saw one: Finktank see the Arsenal win at 70%, the bookies at 61%, and my model at 71%.

So what about the match I'm most bothered about? That is, Carlisle United vs Oldham Athletic. As things stand, the model can't take into account form. If it did, it would put a stronger probability on Carlisle, as Oldham are in terrible form, with four consecutive defeats severely hampering their promotion hopes. Nonetheless, Oldham have a 39% probability of winning, Carlisle a 32% chance, the draw at 29%. What's the most likely score? The probability of a 1-1 draw is 13.3%, followed by a 1-0 Oldham win at 12.6%, with finally a Carlisle 1-0 win at 11%. There's a 10.6% chance of a scoreless draw. All these orderings are the same as Finktank for this match, although Finktank put Oldham slightly stronger favourites at 41%. As part of my summer research I'd like to look into what exactly Finktank construct their forecasts based on, since they're not massively different from that of a "simple" double Poisson model.

I'm biased. Three or so years back, Oldham recovered from a poor run of defeats to post a battling 1-0 win at Gillingham. I think Oldham will do that today. No, I hope.

Finally, Finktank suggest you should believe their score predictions because they've beaten the bookies on a lot of occasions. Personally I think you should trust the output of a model by whether or not it predicts the score well. So I'll let you know how I do.

Labels: , , , , , , ,