Political Football

Once again most of the proprietors of the Sunday newspapers have kept their money in their pockets and left the field to NOP in the Sunday Times, who have Labour on 49%, the Tories on 30%, Lib Dems on 14% and others at 7%. Our model projects this to a 235 seat Labour majority, the BBC's natty model (worth a look) has it at 227. On ours, this result would cost the Tories 19 seats off their 1997 165, add another 28 to Labour's 419, and drop the Liberal Democrats by 8, from 46 at the last election.

NOP also found that if asked to take part in a referendum on the Euro, current attitudes suggest a vote of 69% No, 31% Yes, after reallocating the 11% who say they are undecided. However when asked if they thought Britain would eventually join, 53% thought we would, while only a third, 35%, thought not. Maybe Hague's right.

WINNER: As a bit of light relief for the Bank Holiday Weekend, I'd like to share with you some political sagacity developed by my colleague at MORI Dr. Roger Mortimore, who knows more about the political implications of the national sport than I do.

Professor Robert Mackenzie (a Canadian you'll recall) was once quoted as saying that he enjoyed election nights in the same way other people enjoyed the Cup Final. Roger developed a prediction model for determining the outcomes of British general elections, which over the period since 1950 has as a record to match Bob Mackenzie's swingometer. All you have to do to predict which of the major parties will have an overall majority in the Commons following the election is to note the shirt colours usually worn by the current holders (on election day) of the FA Cup. If their shirts are predominantly in the Conservative colours of blue or white, a Conservative victory will ensue; on the other hand if the predominant colour is red or yellow, Labour will be successful. (Black stripes are ignored.)

The table shows that the Tories win an election held when the FA Cup is held by a club who play in predominantly Blue or White shirts; Labour wins when the cup holders wear a shade of Red or Yellow. A hung Parliament results when the Cup holders wear both parties' colours.

* Would have been correct if Brighton & Hove Albion (BLUE) had not missed an open goal in the dying seconds of the FA Cup final, before losing the replay.

Roger christened this his Sweet FA Prediction model, which he says has failed only twice over the last fourteen elections; furthermore, the sensitivity of the prediction method is demonstrated by the election of February 1974, which produced the only post-election hung Parliament since the War -- that election was fought when the cup holders were Sunderland, whose striped shirts are red and white in equal measure. The obvious improbability of such a pattern arising by chance gives the model a high degree of statistical significance.

Or perhaps not. The point of this jeu d'esprit is to demonstrate that it is possible to find an apparently statistically significant pattern in almost anything, given a sufficiently free hand. (Rather as certain scholars discovered "hidden messages" to prove that Francis Bacon wrote the plays of Shakespeare; Mgr Ronald Knox, when he set his mind to it, was able to use the same methods to "prove" that Queen Victoria wrote Tennyson's In Memoriam.) Of course, even this degree of freedom is not enough for some; at the next election we shall have, as we always have, predictions aplenty by methods that cannot claim even the semblance of a track record: astrology (in 1997, one astrologer confidently predicted John Major's victory on the basis of something called the planet Rahu); "voodoo" polls (prizewinner last time the Tesco "Electoral Roll" poll with a predicted 13% share for the Monster Raving Loonies); "on the basis of history". (Dr David Carlton was undisputed loser of the 20 Reuter's experts in 1997, who even at the last predicted a hung Parliament because he believed history showed that a swing big enough to give Tony Blair a majority was impossible).

Of course, not all methods of prediction are so crude. The absent without leave "Kellner-Sanders" index (at www.yougov.com and which used to be reported in the Observer) has a greater degree of sophistication, based on a combination of opinion poll results and economic indicators. But as one of its two originators, Professor David Sanders, knows, the most elaborately tried and tested economic formulas are not necessarily proof against the anomalous behaviour of the British electorate. (In 1997 Professor Sanders, using economic formulas which had worked successfully for predicting election results in the 1980s, was Dr Carlton's nearest challenger for the Reuter's wooden spoon.). If you want any further comment on the efficacy of the 'economic determinate model', please discuss it with President Al Gore, who was clearly predicted to win handsomely in the recent American Presidential elections by the adherents of economic determinates like Sanders who operate from this premise in the United states.

It is always possible to construct a pattern which fits the past. But unless it explains the past, in a way which still applies in the present, it will not help predict the future. The initial test of any model must be its inherent plausibility as a causal explanation, and this is a test that relies on judgement, not mathematics; if this is forgotten, "statistically significant" becomes a meaningless, perhaps dangerously misleading, term. Nor is "track record", as such, anything more than a perceptional delusion. (Would the FA Cup model be a jot more plausible if Roger had originally discovered and published it in 1996?)

The political implications should be obvious. The 2000 FA Cup winners were Chelsea, who play in blue. If the election had been held on 3 May, as was generally predicted, Chelsea would still have been the cup-holders, and the model predicts that the Conservatives would have won.

However, the election was not held on 3 May, but instead will be held on 7 June; in the interim, another cup final has been held and the FA Cup is now held by Liverpool (who are nicknamed the Reds for the obvious reason). So was it really Foot and Mouth that caused the election postponement? Or are Tony Blair and his football-loving entourage perhaps a little superstitious?

SINNER: When is a Gallup poll not a Gallup Poll? When, according to a pompous Yank who badgered me over the phone the other day, they don't design it, although they carry out the fieldwork (for the last time I'd think, after clearly badgering the guys at Essex who are running the British Election Survey rolling poll which Gallup carried out the fieldwork for.)

The chap who, lawyer in tow, harangued me about how one Gallup Poll (the one in the Telegraph) is theirs, but the other (for the British Elections Study) isn't, and whether or not it is spelled poll or Poll, it is copyrighted, and I'd better understand this -- or else. I see that the splendid www.essex.ac.uk/bes web site has also been told to sharpen up their act, and is now burdened by clarity about all this, clearly dictated by legalistic minds. What is our business coming to? Used to be we all got along; these days it's a bit fractious. Shame. Guess these folks have never heard that you catch more flies with honey than vinegar.

12 days and counting.