Friday, 8 May 2015

Life no longer in a marginal

Withington was a very comfortable win for Jeff Smith:

Labour: 54%
Lib Dem: 24%
Conservative: 10%
Green: 8%
UKIP: 4%
Mysterious Independent: 0.1%

The outcome was remarkably close to Ashcroft's poll from almost a year ago. If that was a true snapshot then the Lib Dems' impressive campaign was worth all of 2% extra on their vote. It appears their famous incumbency bonus vanished this time, in line with the many other Lib Dem losses around the country. The Predict-o-Matic 5000 clearly requires some adjustment.

The local results are also out, more or less mirroring the parliamentary vote, although locally the Greens were almost level with the Lib Dems (this is actually an improvement in the Lib Dem position from last year).

So with a Labour majority of almost 15,000, it's fair to say we no longer live in a marginal. The only question left is where to move to in time for 2020?

Thursday, 7 May 2015

Life in a marginal: endgame

Lest we forget that it's polling day today, the Lib Dems got up early to remind us:


The scan cannot adequately convey the sheer size and weight of this greeting. It was impossible to see the hallway beneath it. If the election were decided purely on last day polling reminder card area, the Lib Dems would be odds on for a landslide.

The Labour effort looked a bit feeble in comparison:




Still, the same quality card stock. The boat is being pushed out by both teams. And Labour even came to my door to ask how I'd voted.

So what was the result of all these months of persuasion?

I went for Jeff Smith. John Leech was a good MP with a great voting record and I wouldn't be unhappy if he were returned to parliament, but I was put off by his attacks on Labour's economic record and plans. Ultimately I voted for those plans.

In the local elections I voted Lib Dem, as a kind of oblique protest against first past the post. It is unhealthy for all of Manchester's councillors to be Labour, and the Lib Dems are best placed to offer some scrutiny. See? All that propaganda does have an effect in the end...


Wednesday, 6 May 2015

Life in a marginal: polling eve news

Good old South Manchester News has hit the printing presses again just in time for the election.

Well, it's sympathies are less obvious than the national newspapers I suppose.

The Leech campaign is really not doing any favours with me by attacking Labour's entirely sensible if not timid spending plans as "reckless". But never fear, because the man himself has sent us a handwritten note in a final plea for our votes:




Having noted the "P.S."s at the bottom of all his letters, I'm not sure Leech has got the hang of them. They always reiterate what he's already written, when they should say something in passing like:

P.S. I've heard there's free ice cream at the polling station today

or

P.S. Would you stop your dog barking at our canvassers?

Labour go for a more conventional leaflet:



Nothing new to report here. I'm running out of things to say about these leaflets, so just as well it's polling day tomorrow...

Tuesday, 5 May 2015

Life in a marginal: the dark arts

Hmm. An anonymous brown envelope arrives containing all kinds of terrible revelations about Labour. Who could it be from?


I'm guessing it's not from Labour...


I see it's very positive about the Lib Dems' record in government on the back. Could this be a clue as to the senders? Ah yes! They admit all in the very small print at the bottom. I should have guessed from the paper.

Quite why they think this will convince me to vote Lib Dem is beyond me. At least the previous Ferrero Rocher letter was upfront about being from the John Leech campaign. This one is a new low, not only repeating the same old twaddle about Labour causing the financial crisis, but also heavily implying without openly stating that Labour plan to cut more than the Lib Dems in the next parliament, when of course the opposite is true.

Still, if the Lib Dems want to spend good money making it less likely I'll vote Lib Dem, that's their call.

Monday, 4 May 2015

Life in a marginal: canvassing and a revised prediction

Labour continue to step up their leaflet game, sending me a personal communication addressed personally to me in person, a variation on the one received by Mrs Tomsk a while back:



In addition they've sent me my very own personalised polling day information card:




I like the reminder to put an X next to Labour. Also, remember to put some shoes on before leaving the house.

Unfortunately for Labour, the Lib Dems have gone one better again by sending a canvasser to Tomsk79 HQ at last! I learnt an interesting piece of information: that John Leech had not voted for the coalition in the first place.

Naturally being canvassed affects the delicate calculus at the heart of the Predict-o-Matic 5000. Its revised and final prediction is therefore as follows:

(beep beep boop boop boop etc.)

Con: 8%
Lab: 45%
LD: 37%
UKIP: 3%
Green: 7%
Mysterious independent: 1%

(nb: result adds up to 101% in light of the model's continued awesomeness)

Attack of the Also-Rans, Episode 3: the Greens

Finally in our round-up (as I've yet to receive anything from the Mysterious Independent), the Green Party. Again it comes in compact A5 format, no doubt because more eco-friendly. It is of course printed on FSC-approved paper.


No-one does hopey/changey quite like the Greens. Bannister's photo is curiously back-lit, like an angelic character from a Sofia Coppola film, leading us to a Green utopia with a list of the promises you wish Labour would make if only they didn't have to worry about actually winning an election.


On the reverse we learn Bannister is another proud graduate of the University of Manchester, only this time writing with impeccable English. I'd expect no less from someone who studied the king of subjects.

Surprisingly even on the back there is no mention of the environment at all. I suppose this is what they mean by "politics for real people". As a Real Person who occasionally attempts to get to Sheffield using a car, I curse the Greens every time I get stuck in poor un-bypassed Mottram. But I digress...

Attack of the Also-Rans, Episode 2: UKIP


Perhaps the best that can be said about UKIP's election leaflet is that it comes in a handy A5 format. Whether the size symbolises their little England worldview or their chances of winning here, I cannot judge.

The front is essentially a transcript of Davies' opening statement at the hustings:


Many things are said to be the definition of madness. Seriously wayward punctuation. Standing for UKIP in Withington.

Still, I'm intrigued by his wide experience of business AND organization. What is this non-business organization he has wide experience of? UKIP purple always vaguely recalls Wimbledon for me, so I can't shake the notion that it was the Wombles.

Being oop north we get the version of UKIP that is intended to appeal to disgruntled Labour voters, with promises on the NHS and bedroom tax nestled in amongst the foreigner bashing:


I do hope the Australian-style points-based system will allow Madame Cholet to stay.

Sunday, 3 May 2015

Attack of the Also-Rans, Episode 1: the Conservatives

At last the Lib Dem/Labour leaflet duopoly has been broken, with all three of the other parties' free communications arriving on the same day.

First the Tories. Receiving a leaflet with hues from the other side of the rainbow is a refreshing change for the eyes, even while the content makes them burn.


Manning's cover letter (as ever, click to enlarge) is undermined by some terrible grammatical howlers. "investment ever more in our NHS"? "Liberal Democrats set to loose many of their seats"? I expect better from proud graduates of the University of Manchester! With all the gazillions of pounds being poured in to the party by hedge funds you'd think they'd be able to hire someone to proof-read their sales pitches.

On the other hand I quite enjoyed his subtle trolling of the yellow team: "It is not clear that the Lib Dems will be able to support a Conservative government again". Heh.



The Northern Powerhouse gets name-checked in a small paragraph on the reverse. I'm surprised he doesn't make more of it given that it's a genuinely Good Thing and very much associated with George Osborne and the Tories rather than their coalition partners.

Finally a dodgy bar chart of the Conservative variety. Quite apart from the current economic recovery being the slowest since dinosaurs ruled the earth, I'm not at all sure that the G7 covers every "major economy" these days...

Saturday, 2 May 2015

Life in a marginal: my poster's bigger than yours

An increasing focus on local elections as Labour send me a leaflet advertising the Jeff Smith/Matt Strong two candidate combo deal:


Good stat work there with the claim that the Lib Dem candidate (who he?) has voted with the Tories 93% of the time in the last parliament. Just guessing but I imagine it's the other 7% of votes that are the important ones.

More exciting is the other side of the leaflet which doubles up as a poor man's window poster:



Even if I was in a poster-displaying mood I think I'd be too embarrassed to put one up featuring text-speak, but I have seen them go up in a few windows so clearly it's a worthwhile use of leaflet space.

The Lib Dems, however, have trumped these puny A4 signs with a supersized hashtag in the middle of Chorlton:



I thought political hoardings died out sometime in the mid-90s and spotting one this time round would be as likely as ever hearing a new Blur album. We live and learn.

Friday, 1 May 2015

The Manchester Withington Predict-o-Matic 5000

http://www.mosi.org.uk/whats-on/meet-baby.aspx

The 2015 election has been notable for the many new models attempting to predict the result, mostly created by academics trying to avoid doing any proper work. In that spirit we at Tomsk79 have created our own model for predicting the result of the Manchester Withington constituency, which is detailed in full here.

The starting point for my model is the constituency poll carried out in June 2014 by Lord Ashcroft (blessed be his name). This poll suggests a decisive swing from the Lib Dems to Labour since the election:


The next stage is to correct the Ashcroft poll by movements in the national polls since June 2014. For this we use the BBC Poll of Polls, which reports changes as follows:

Con: 31 to 34 (+3)
Lab: 34 to 33 (-1)
LD: 10 to 9 (-1)
UKIP: 15 to 13 (-2)
Green: 5 to 5 (0)

We assume that the national changes apply uniformly to the Withington constituency.

Next, we apply a sub-seat correction using local election results from Withington wards. By analysing trends in council results from 2010-2015, we can divide the Ashcroft results up by ward and apply corrections that can be projected to polling day. This results in a single party state correction (SPSC) which we calculate to be +1.4% LD to Lab for next week's election.

Another important data input is the normalised voter contact ratio (NVCR), which we estimate based on leafleting frequency. Assuming the Tomsk79 HQ is typical of Withington households, each voter receives 11 Lib Dem communications and 5 from Labour, giving an NVCR of 1 / (2.2^2) = 0.21, which corresponds to a 5.2% Lab to LD swing.

Once the SPSC and NVCR have been applied to the whole seat prediction, we can then take into account historical trends in polling time series, including reversion to the mean or 'swingback' and marginal-indicated protest vote propensity (MIPVP). According to our tailored swingback model we expect a 2.3% Lab to LD switch over the period of the short campaign, and a time-static boost of 2.7% for the Greens and 0.8% for UKIP overall from MIPVP.

The last macrocorrection we make is to compensate for electorodynamic effects (rather than kinetic effects as in the previous corrections). As electorodynamic data is not readily available from polling or ground observation, we estimate it using a Frequentist-uprated Dynamic General Equilibrium model. This suggests a 0.06% LD to Lab swing and a "Green squeeze" of -0.4% which is shared 0.3% to Lab and 0.1% to LD.

We now turn to local environmental and geographical issues. First, we correct for the weather forecast next Thursday. It is well known that Labour voters cannot be bothered to turn up at the first sign of drizzle, and at the time of writing the BBC weather forecast for Withington is reporting light rain showers for polling day. Using the Fitzroy-Shannon model developed by the Met Office we calculate a weather-related voter intention depression (WRVID) of 0.3% to Labour's vote and renormalise the other parties accordingly. Naturally WRVID can be refined as we get to closer to the 7th, but we do not expect it to change significantly given that the constituency is in Manchester.

So far in our model the calculations have been computationally trivial, but with modern levels of parallel compute resource we can go beyond simple seat- and ward-level predictions. We can in fact model individual voters using our own purpose-built agent-based simulation, which combines the Mosaic voter profiling system with Hawk-Eye trajectory analysis technology. Through this we can predict individual voter trajectories right up and into the polling booth with unprecedented accuracy.

Naturally the resulting trajectories are classical and do not take into account any quantum fluctuations that may influence the result at a causational level. We therefore apply a quantum correction to the Mosaic/Hawk-Eye trajectories via a quasi-classical approach, using Ehrenfest's theorem under the constraint of Duverger's law.

Finally, we use a statistical technique called Tea-Leaf Analysis (TLA) to apply a low-pass filter over all the previous corrections, thereby deconvoluting most sources of noise.

So, after all that number crunching, what is the predicted result? For no extra charge I've converted the punchcard output into human-digestible numbergrams:

Con: 8%
Lab: 47%
LD: 35%
UKIP: 3%
Green: 7%
Mysterious independent: 1% 
(nb: result adds up to 101% due to the excellence of the model)

In conclusion, we believe the Predict-o-Matic 5000 to be the most accurate constituency prediction system ever devised. Indeed our analysis indicates an 80% chance of the model being more accurate than reality itself. Any error in the final result is therefore likely to be a fault in the universe rather than a problem with the calculations.