The Scottish Independence Referendum, 18th Sept 2014

[djewesbury]

I will be staying up to watch the results come in, and I have prepared myself an appropriate tasting, comprising of six bottlings from the Scotch Malt Whisky Society's outturn:


If you are also going to be in front of your TV that night, please join me and tell me what you're drinking.

[DRT]

Impressive lineup.

I will be up and watching in my hotel room in London. I will pop down to my local off-license to pick up an appropriate bottle to see me through the night.

[djewesbury]

Impressive lineup.

I will be up and watching in my hotel room in London. I will pop down to my local off-license to pick up an appropriate bottle to see me through the night.

Excellent. We'll both be really useful come Friday. Hopefully we won't also be in a really foul mood.

[DRT]

Impressive lineup.

I will be up and watching in my hotel room in London. I will pop down to my local off-license to pick up an appropriate bottle to see me through the night.

Excellent. We'll both be really useful come Friday. Hopefully we won't also be in a really foul mood.

It's a safe bet. At least 60% "no". I have it on good authority from Rab McGabe.

[PhilW]

That's quite a selection. I picked up another bottle of the Balvenie Caribbean cask today, since Sainsbury's have it reduced at the moment, so I'll either be celebrating the decision to stay, or toasting all the best for their decision to go forward independently.

[jdaw1]

Is the X to indicate a choice, or a negative choice?

If it is a No, I do hope that post-event surveys show that some voted No because of the vehemence of the Yeses, in particular their harassment of those who disagree.

[djewesbury]

The X is primarily a ballot paper mark but it is also, happily, an inverted saltire (albeit one in grey and white). You may know by now which way I lean on this issue (clue: Ian Paisley used to like this word) but how you choose to read the symbology of this placemat is a matter for you as reader to decide.

[djewesbury]

I also happen to think that Gordon Brown wrote an excellent piece in yesterday's Grauniad explaining why the UK is the best vehicle that citizens have if they want to be able to direct, or influence, the extra-territorial forces shaping our society today.

[DRT]

I do hope that post-event surveys show that some voted No because of the vehemence of the Yeses, in particular their harassment of those who disagree.

Indeed. I was in Edinburgh last weekend and was told by a number of people that many of those intending to vote No are keeping silent (or lying) to avoid the venom of those who are of a different view. That is the reason for my confidence in at least a 60/40 victory to No.

[djewesbury]

I do hope that post-event surveys show that some voted No because of the vehemence of the Yeses, in particular their harassment of those who disagree.

Indeed. I was in Edinburgh last weekend and was told by a number of people that many of those intending to vote No are keeping silent (or lying) to avoid the venom of those who are of a different view. That is the reason for my confidence in at least a 60/40 victory to No.

Yes, something about this reminds me of the 2008 US election. Everyone said that it would be too close to call or a McCain victory. Only one analyst, Nate Silver, called it correctly, by looking at the biases of all the polls and studying what all the data from them actually told him. I don't think it'll quite be 60:40 this week but I don't believe either that it's going to be as close as the media continually say it will be. Where is the proper analysis of all this woefully inadequate polling data?
I am delighted to hear that McGabe has today said that he will not call for endless repeated referendums if he loses. (NB: referendums. Not referenda. It's an English word.)

[PhilW]

I was in Edinburgh last weekend and was told by a number of people that many of those intending to vote No are keeping silent (or lying) to avoid the venom of those who are of a different view. That is the reason for my confidence in at least a 60/40 victory to No.

I can certainly believe that many "no" voters are keeping their heads down, primarily because the issue seems to be being treated as if it is a "vote yes if you're proud to be Scottish" by many, perhaps deliberately/divisively, rather than about the independence itself. However, I can see the "proud Scottish yes" vote winning the day (rather than a "yes to independence"), so I am less confident in the result.

[DRT]

Where is the proper analysis of all this woefully inadequate polling data?

There are some who have diligently analysed the available data and reached a well informed conclusion...

Screen Shot 2014-09-14 at 17.37.39.png (44.35 KiB) Viewed 14422 times

That is quite a margin in a two horse race. They are seldom wrong.

[djewesbury]

Crikey!

[PhilW]

That is quite a margin in a two horse race. They are seldom wrong.

If they are, do we have to bail them out at tax-payers expense, or is that just for other types of gamblers? I admit I'm surprised by the margin there.

[jdaw1]

That is quite a margin in a two horse race.

Innumerate rubbish.

Odds of 1/4 and 3/1 imply probabilities of 80% and 25% (the total exceeding 100% by the bookies’ profit). So divide by 1.05 to get implied probabilities of 76% and 24%.

Let’s assume that the Yes and No votes are normally distributed, with a standard deviation of ±5% (this σ having been guessed by me). So if the expected outcome were 53.6% : 46.4%, with that uncertainty, the probability of a Yes would indeed be about 76%. But 53.6% : 46.4% is quite a small margin.

= 50 + 5 * NORMSINV( 1 / (1+(1+1/4)/(1+3)) )

[DRT]

please define standardly distributed.

Normally distributed. It’s not, of course, very little is, but the approximation isn’t going to mislead.

If you want to attack, attack the ±5%.

I certainly don't want to attack you on a calculation. I was simply observing that when bookmakers create such a gulf in odds in a two horse race there is very little probability that the outsider will win and the favourite, in such circumstances, very often wins with ease.

[jdaw1]

Some posts moved to Lies, Damned Lies and Meaningless Drivel by jdaw1.

[djewesbury]

Some posts moved to Lies, Damned Lies and Meaningless Drivel by jdaw1.

Thank you.

[LGTrotter]

I was in Edinburgh last weekend and was told by a number of people that many of those intending to vote No are keeping silent (or lying) to avoid the venom of those who are of a different view. That is the reason for my confidence in at least a 60/40 victory to No.

I can certainly believe that many "no" voters are keeping their heads down, primarily because the issue seems to be being treated as if it is a "vote yes if you're proud to be Scottish" by many, perhaps deliberately/divisively, rather than about the independence itself. However, I can see the "proud Scottish yes" vote winning the day (rather than a "yes to independence"), so I am less confident in the result.

The same issue as the 92 election where people were a little shamefaced about saying to pollsters that they were voting Tory, but they did.

Not being much into spirits I am at a loss what to drink. There are the Scottish port shippers, or at least of Scottish origin.

[djewesbury]

Scottish port importers were many and varied but the bottles are fairly rare now. Shippers gives you obvious choices though; even Taylor and Croft could be said to have Scottish links via various different Robertsons.

[DRT]

Scottish port importers were many and varied but the bottles are fairly rare now. Shippers gives you obvious choices though; even Taylor and Croft could be said to have Scottish links via various different Robertsons.

Anything currently made by the Symingtons would do.

[AW77]

Sandeman's (I hope the apostrophe is correct in this case) has Scottish roots as well. So you could even have a Sherry (or stick to port).

[LGTrotter]

And does anyone know when the result will be declared? Not sure where exit polls fit into this one either, if there are we could still all get an early night.

[djewesbury]

And does anyone know when the result will be declared? Not sure where exit polls fit into this one either, if there are we could still all get an early night.

The count will begin as with a general election, almost immediately, but depending on the maths there could be no result until 7 am. And I'd be very wary of exit polls.

[DRT]

I suspect we will know in roughly the same timescales as a general election. The Highlands and Islands could drag into Friday but there is no one there so that doesn't matter.