Posts by linger
Last ←Newer Page 1 2 3 4 5 Older→ First
-
Hard News: Where are all the polls at?, in reply to Ianmac,
There's some degree of feedback, most often taking the form of consolidation on the poll-anointed "winner" at the expense of poll-anointed "certain-losers" — though probably just as much through encouraging voter abstention as through encouraging an actual switch in support.
-
TL;DR — the expected effects on errors in support estimates arising from lower overall support rates (lower p, hence lower theoretical variance) and regional/demographic restrictions on support (hence lower effective sample size, and higher theoretical variance) seem in practice largely to cancel each other out in NZ data.
-
Hard News: Where are all the polls at?, in reply to mpledger,
Not disagreeing there — see the last few lines of my comment above. Theoretically extreme case: if a minor party’s support were entirely limited to a small, definable demographic or regional subset of the population, then the relevant sample size for calculating the error in that party’s estimated support would be the (unknown, but much smaller) size of the subsample obtained for its demographic, rather than the overall sample size. Hence the error for smaller parties with restricted support bases should be larger than that predicted from the overall sample size, all else being equal. But in reality, such restrictions on party support are probabilistic rather than categorical, so that approach will overestimate the error. The empirical proof is there in Lumley’s results, which show less variation (on an absolute scale) around figures for the smaller parties.
-
Hard News: Metiria's Problem, in reply to Rich of Observationz,
Oh. I read Sacha's question as "How would closing them down be popular?" and assumed you were merely being sarcastic on that point.
-
Hard News: Where are all the polls at?, in reply to Bart Janssen,
for smaller parties the polls are less accurate
Only in terms of relative error, not in terms of the absolute error. The theoretical variance, and therefore the theoretical margin of error, in a proportion estimate is proportional to p(1-p), so is largest for p=(1-p)=50%, and falls as either p or (1-p) decreases. Lumley’s results (referenced by mpledger above) do not show any larger absolute error in poll estimates for smaller parties; indeed, he explicitly states the error should be largest for National because its support is nearest 50%.
Now, it might well be that in some polling methods the sample is less likely to be representative of certain minority voting blocs, and/or the reweightings applied might not adequately correct for that, and so estimates for parties with support concentrated in specific demographics might be less reliable — but that’s a separate issue from effects resulting only from lower overall support. -
Jane Bowron goes completely off the rails in today’s Dominion Post (p3, “Motels, memorandums and dunny misalliances”; the online version has a different title). She starts promisingly enough by noting that Greens have NOT sought any electorate lifeboat from Labour despite “disaster polls” … but then spends four slanderous paragraphs imagining that Shaw did just that in Wellington Central, using her fabrication as a platform from which to mock the Greens as “unsustainable” and a “pity party”.
Is it too much to ask supposedly serious political commentators not to veer into pure fantasy? (Note also the exaggeration of “disaster polls” – I thought there was only one unexpectedly low result so far?) -
Speaker: Low-quality language on immigration, in reply to Katharine Moody,
popular myth
Well, not sure if it's really all that popular, except among the rich pricks that dominate the commentariat (so it gets a lot more airplay than it should); and in some sectors a lack of trained individuals is a reality rather than a myth (largely the result — as others have noted above — of the past 20 years of user-pays education and the dismantling of continuing-education programmes) ... but it's certainly part and parcel of Blinglish's bullshit about dole recipients being unskilled lazy druggies.
-
Numerical system diversity
What does that include? Unit conversions should be straightforward enough (though not doing them has resulted in several expensive accidents). Are there any other tricks to handling American-sourced data (oh, other than their idiosyncratic date order convention)?
-
Hard News: Metiria's Problem, in reply to mark taslov,
Exactly. Whatever side of the house the Greens end up sitting on, our Parliament would be a much poorer place without those voices being heard at all. We need them to be there, and that may well mean voting for them.
-
In a truly bizarre overreaction, I/S argues that the Greens should be aggressively pursuing electorate as well as party votes. That would only make any sense if there were at least one electorate that the Greens could hope to gain a plurality in; and it would only make sense within some such electorate(s). Otherwise it's a waste of their resources: if they can't win one electorate as a backup plan, then they absolutely need all the party vote share they can get.