Posts by Graeme Edgeler
Last ←Newer Page 1 2 3 4 5 Older→ First
-
Hard News: Calling the race before it's over, in reply to Matthew Poole,
It would certainly explain why NZF is polling at fractions of the margin of error.
The last Colmar Brunton Poll had NZF at 4.9%. With n=856 for the party vote question, this poll alone gives NZF a ~46% chance of making it into Parliament.
-
Legal Beagle: MMP Review #1: The Party…, in reply to Steven Peters,
From your knowledge, has any attempt(s) been by government/parliament to consider any of Bostons recommendations, or even more generally look at constitutional issues ” In the interests of ensuring a more orderly process of government formation, reducing political uncertainty and enhancing government durability”, under MMP
There have been some discussions around a fixed term, but I don't know of everything else being discussed within government.
-
I will add my thanks to David Hood, for programming the Referendum tool!
-
Hard News: The Big 2012 US Election PAS Thread, in reply to BenWilson,
Perhaps I’m missing something subtle in here. What does “92% likely” actually mean, in this case? Because “foregone conclusion” to me means “100% likely”.
My question too.
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Bart Janssen,
But whatever method he used you can’t simply take the 92% and treat it like a dice roll. It is not necessarily true that in 8 elections where he predicts a 92% chance he will have a 50% chance of being wrong.
If being 92% certain of something doesn't mean there is an 8% chance of something else happening, what does it mean?
I assume it acknowledges that there is at least a chance of something else happening? So if you have enough elections, at some point, there will be a 50% chance of you not picking 100% of the races correctly. At what number of elections does that happen for elections, all of which have a 92% certainty?
I had understood, though I may be wrong, that the group of results from each possible sample of a population would be normally distributed.
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Kyle Matthews,
But rolling dice is random (at least, in theory, I guess it’s actually a result of physics, the nature of the dice, the nature of the surface it lands on, and the way it gets thrown) at the time the dice gets thrown.
Elections aren’t random. If 90% of people have chosen how they vote a week out from the election, then polling can send very strong signals.
And the polling are random (at least in theory). You ask 1000 people a question, 9 other companies are 1000 people a similar question, and if you get a result that's really kinda close, maybe the reason that one candidate is head among those 1000 (or those 10000) is a result of the fact that random samples aren't always representative samples, and even though 90% of people had made up their mind, you didn't actually ask a politically representative part of that 90% so when - even though no-one has changed their mind - the election came around it didn't pan out exactly as you expected.
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Bart Janssen,
To describe the Obama win as anything other than the expected result at any time this year would have been false.
Expected result and forgone conclusion are not the same thing.
I agree that Obama’s re-election was certainly expected.
If I roll two dice, I expect I will roll something less than 11. But rolling a 10 or a 9 or an 8 or something lower is not a foregone conclusion. There is a smallish, but very real chance I will roll an 11 or a 12. And on Nate Silver’s numbers, he was telling everyone he thought the same about the presidential race: confident Obama would win, but not certain. Just like me and those dice.
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Russell Brown,
Under Romney?
Should I have said "the possibility"?
Maybe Romney would have gone back to (or toward?) Bush levels of persecution? Maybe. Because I don't think Obama is, so even the possibility has something going for it.
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Russell Brown,
I mean, a trade-off compared to what? What was the actual alternative on offer?
The possibility that the trajectory around whistleblower persecution would alter?
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Russell Brown,
Although … I’m not sure that a future where elections are forgone conclusions is actually all that healthy either.
It wasn't a foregone conclusion. If there are 9 elections where someone is a 92% to win, there's a greater than 50% chance at least one of those elections will see an upset. But which one, or will it be two, or none :-)