First of all: there will be more than one exit poll exercise on Tuesday, and some of the smaller independent exit polls will be specifically designed to shed light on the integrity (or otherwise) of the vote-counting process.  But the big one will be the Edison-Mitofsky poll for the NEP (National Election Pool], so this diary is about that.

I don't know New Orleans, hell, I don't know America, I'm a Brit. But being a European means that like most Europeans, I have a bit of a different perspective on the life and death of cities.  And I'm worried about New Orleans.

Disasters don't generally kill cities.  London was ravaged first by plague, then razed by fire, in 1666.  The fire not only burned the thatched, timber-framed houses to the ground, it destroyed the ancient cathedral of St Paul's.  And yet St. Paul's was rebuilt, mostly within Wren's lifetime, and its dome is iconic of the city.  Florence was devastated by flood in 1966, as was Venice, a city built over water.  Although loss of life was small, both cities lost priceless artworks, although many were painstakingly restored.  Both cities are as alive as ever today.

Dresden, Hamburg, Hiroshima, Nagasaki were all destroyed in the second world war.  All are thriving cities today. And Holland survives as a nation below sea-level by virtue of a constantly maintained system of levees and pumps.

So why am I worried about New Orleans?  

This is an exit poll story, about trying to get to the bottom of why the early exit polls in the 2004 US presidental election over-estimated Kerry's share of the vote, an especially painful overestimate because unlike an error of comparable magnitude in 1992, where the exit polls also over-stated the Democratic vote, the difference in 2004 was the difference between defeat and victory. It's a geeky story, because it's about a tiny mathematical piece of the puzzle - but a piece that may be crucial to interpreting the data.  And it's a blog story, because that tiny piece emerged from the collective networked wetware that is the blogosphere.

Read on....

Come and join us!  We're discussing the UK election.

Tony Blair and Gordon Brown have already got a drink....

...but there are still a few seats left near the fire.

Here it is

and recommend it when you get there, so's we can get a good fug going.

The Tory manifesto came out today - they want less immigration, cleaner hospitals, and stricter schools.  No sign of wanting to teach creationism as science, thank God. Howard looks like Dracula grinning from the inside cover (they don't want to risk putting him on the outside). Blair and Brown are pretending the Iraq war isn't happening, and that the country's blooming.  Charlie Kennedy's wife's about to have a baby.

Whose round is it?

The 64 million (or is it billion?) dollar questions is: which was wrong, the polls or the count?

"Fraudsters" claim it was the count.  Edison-Mitofsky (and the "anti-fraudsters") claim it was the exit polls.  In this diary I have a brand new analysis.  Bear with me, even if you find math icky.  There will be pictures, if not cookies.

I just received this message from Tony Blair:

More below:

This is a primer for Welshman's promised series (with me, Febble, not Hebble) on the forthcoming general election in the UK. As there was quite a bit of interest shown in the series, it would be good to get some recommends so that this diary can stay up long enough for those interested to see it - thanks!

Britain, notoriously, and unlike most sensible countries, has an unwritten constitution. This, I am rapidly discovering, is because when you write it down it looks so bloody daft.

The Lord Chancellor presents the Queen with her speech (written by the prime minister), inscribed on goatskin.

However, here goes:

And that is not working from screen-shots, that is working from the data presented in the Edison Mitofsky report.

Not only that, but it happened in 1996 too!  A one in 268 probability of occurring by chance!

And in 1992! A one in 5007 probability of being due to chance!

And in 1998! A one in 49,827 probability of being due to chance!

Er, that's funny, what happened in 2000?  Oh, here it is -  yes, polls were wrong again! Only 1 in 3 probability this time, though.

But get this - they all made the same error!  Yes, that's right, they all over estimated the Democratic vote!  Even in 2000.

So what can we conclude from this?

Read on.....

He is offering some sympathy for Lord Goldsmith, the attorney general, who provided legal advice to the British government regarding the legality of the proposed war:

More below:

Here are my questions, and my credo (for today at least):

I asked Google to sort hits by date, not importance, so I got any breaking news.  But this meant that I got all the little local rags and blogs.

At first there was very little.  Then there were a few days (over the weekend) with a lot of identical entries, showing that syndicated columns were being widely published.  

But today and yesterday all the entries started to look different, and although some are syndicated, there is obviously a lot of in-house writing going on too.  In fact there is a lot of writing period.  For links to articles logged by Google in the last 20 hours see below the fold:

But I wonder if he wants more than a dinner ticket.  

There is some good news below the fold:

Most of her evidence looks to me to be utterly damning of the electoral process.  But being a stats nerd, I got hung up on the stats, and I don't think the exit poll arguments are up to the watertight standards of the rest of the paper.  So, for what it's worth, here are a few specific quibbles, mostly with Freeman's very gung ho probability values.

With statistics, in general, you want to make the most conservative assumptions you can get away with to make your argument.  I've done this where I could.  More below:

The reason I started doing this was that although there is plenty of thoughtful liberal theology out there, written for lay adults, there is very little for kids, and when my son was born I just didn't want to be feeding him stuff that I didn't believe myself.  

Mystery pollster has done a far better job than I ever could at explaining issues relating to the exit poll discrepancies.  However, the paper recently posted by Ron Baiman at Free Press has not yet been critiqued by Mystery Pollster, so I have had a look at it to see how it squares with the principles laid out by Mystery Pollster.  Baiman kindly sent me the spreadsheet he was working from so I was able to see what he had done.

One woman, referred to as Leyla M, is 18 years old, with a mental age of 8.  

More below: