Posts by steve black
Last ←Newer Page 1 2 3 4 5 Older→ First
-
Hard News: The Big 2012 US Election PAS Thread, in reply to Bart Janssen,
In case anybody is still interested in the 92% all these hours later...
I'm your friendly resident statistician. That's the good news. The bad news is I haven't read Nate Silver's methodology yet. But if the description of it as a Monte Carlo simulation is right then I can help you. I used that technique for my Masters Thesis, although they made me do "real work" for my PhD because "simulation" wasn't considered real enough back then before the revolution.
Then they add up the number of times they see a given result, in this case 92% of the times they ran the model it said Obama won.
Exactly so. The 92% is an enumeration of the outcomes for the simulation in which Obama won as a percentage of all outcomes. This stands in for a probability. Again, the important thing is that the model is properly constructed and range testing on assumptions is adequate. It is even possible (but much more work) to construct confidence limits for the 92%.
But you simply can’t treat it like a dice roll or coin toss and say they’ll be wrong once every 8 or 9 elections. It just isn’t that kind of stats.
Spot on. The concerns about being wrong 1 in N elections are not well founded. Sounds like the law of averages at work to me. 2016 is not another "coin flip" following on from 2012, and there is no chain of probability. Once you get past very simple probability models it is advisable for professionals like doctors and lawyers to consult professional statisticians. We wouldn't want another Meadow incident would we?
And I wouldn't be as kind (diplomatic?) as Russell is:
I would just like to point out that when Corin Dann explained this story to One News viewers this week, he said that Nate Silver had forecast that “Obama will win by 92%”.
This data journalism thing clearly has a way to go yet.
This kind of reporting does not meet the professional standards for accuracy. Allowing "Obama has a 92% chance of obtaining enough Electoral College votes to become the President" to morph into “Obama will win by 92%” isn't good enough. Sloppy. Not uncommon. But still Sloppy.
-
Thank you Russell, what a great laugh.
Thankfully Jon Stewart jumped in and wrapped up the interview with Nate Silver before Nate finished telling the Republican strategists the list of things they needed to change to win the next election. Not that they would necessarily listen, but hey, let's not make it any easier.
"Statistical thinking will one day be as necessary for efficient citizenship as the ability to read and write." – H.G. Wells
-
I’ve been waiting for some turnout figures. Wikipedia has a long time series of historical data, but nothing for 2012 yet. I seem to remember hearing about a “good” turnout, or was it even “big” turnout from those commentators, but I want some numbers. I can add up the 60,662,174 plus 57,820,742 the Huff Post show, but it would be really good to find out by ethnic group and gender. The exit polling must collect those demographics.
The historical figures make interesting reading. Looks like less than 60% of the Voting Age Population do vote, but even more interesting is the fine print at the bottom which suggests that up to 10% of Voting Age Population don’t qualify to vote. Then you also have to be registered… I know from comparative studies that the US isn’t alone in having low voter turnout.
I did find one interesting article saying turnout was down
-
OnPoint: H4x0rs and You, in reply to Lucy Telfar Barnard,
The one exception to this, to my relief, has been reporting of public health research findings. I think it’s the SMC that makes the difference.
That’s certainly not my experience, although I can’t comment on how much the Science Media Centre might make a difference (no separate experimental control group ;-) ). Reporting of public health research can be seriously off. Do you read StatsChat (U of Auckland)? Examples are legion. Most recently:
And for a more entertaining exposition enjoy this Ted lecture (sorry I don’t know how to include the link with little preview window):
-
OnPoint: The Source, in reply to Steve Barnes,
So do we now think MSD is an acronym for Ministry of Secure Data? If that catches on they may have to rename it. Again.
-
I've recently been watching the Yes Minister series from the beginning. I see I will be able to pause my (legally purchased) DVD and watch the real thing for a time. It is fun comparing the two.
Please pass the popcorn.
-
I was recently reading up on the 1951 Waterfront Dispute. Scary how much of what is written up there is still true today.
-
Hard News: This Is Not A Complicated Issue, in reply to Helen Miller,
BTW NZSL is the country’s third official language...
From the stranger than fiction department: I know Te Reo is an official language, but I think you'll find that English is not an official language. I heard that some time ago from a linguist discussing preservation and support for languages on NatRadio (long before this event). It turns out that "official language" actually means "a language other than that of the dominant group which we feel we ought to help preserve/foster". Enjoy the irony if it checks out. ..I haven't tried to fact check it yet.
Meanwhile, at times like these I always stop to ponder the options:
Is Lockwit completely unaware of the likely media consequences of his utterances? His approach is rather like announcing you are "against mom and apple pie" while campaigning in the American Midwest. Or announcing that you have just developed a new way of moving babies more quickly and at lower cost...using pitchforks.
Or is he doing this so that the Government can use it's not unheard of ploy of announcing something draconian so that they can then negotiate to something acceptable and look reasonable?
Is there something even more odious about to be released to the public from the Govt and they are hoping that it will come out during the next news cycle or two which is dominated by DeafGate? This is from the same people who brought you "two johns two cups" .
Something else? (suggestions welcome)
-
Speaker: Doing the right thing on retirement, in reply to Richard Aston,
But what about a finer tuning of super – asset testing, income testing or even basic needs testing…
I know many people who are asset rich, have incomes ( investments) and consider getting super a nice little bonus. Surely that just does not make any sense.
…don’t tell me its too complicated to test eligibility, the IRD are masters at in in other domains.
It usually doesn’t make sent to people that Don Brash and John Banks (to pick two random examples) get National Super when clearly they don’t need it. But I’ve been told that the abhorrence of means testing, asset testing, and income testing come from odious use of these things in the last century by Government Departments like Social Welfare. I didn’t come here until early 1975 so I only know what I’ve heard. But I was just in time to watch Muldoon scrap the mandatory super scheme and tell businesses to stop contributing. Interestingly, my legal friends tell me Muldoon was inciting criminal behaviour by employers when he told them to stop contributing before the legislation went through to cancel the scheme.
-
Legal Beagle: Referendum Fact Check 4:…, in reply to Rich of Observationz,
I understand with compulsory voting, the Aussies regard anything from a tick instead of a cross to drawings of penii on the ballot paper as an “informal vote”?
An “informal” vote is commonly called a “donkey vote” in Australia, which raises interesting questions about the size of organ which might be drawn.
I've often wondered (but never found out) what proportion of votes are "donkey votes". What if it were the same proportion as registered voters who don't turn up to vote here? Compulsory voting might not have succeeded in improving turnout.