On the move!
Agh! You’re still here? My new site and weblog, ianking.ca is now up and running; new posts are building up over there, never to be mirrored here. Go! What are you waiting for? All the stuff worth keeping has been migrated over to the new server, and I don’t anticipate making any more posts here.
Bloggers and webmasters: Update your links! Simply replace vancouverscrum.blogspot.com with www.ianking.ca in your blogrolls or bookmarks to point to the new site. Old posts will remain on this server for as long as the people at Blogger/Google allow them to remain; unfortunately, I’m not going to bother to come up with any way of converting permalinks on this blog to their corresponding posts on the new site. Yes, I plead laziness. I also realize the irony of switching away from Blogger just it starts to add features that the demanding blog nerds insist upon.
Thanks for reading and linking, and see you over at ianking.ca!
—Ian King, December 13, 2004
Sunday, June 27, 2004
EPP Weighs In
EPP was accurate in over 92% of the ridings in the 2000 federal election; they've had similar success in provincial elections in BC and Ontario, as well as the most recent UK general election. Their attempts at predicting the races in New Brunswick and Quebec haven't been as successful, most likely due to a limited number of project participants. Both NDP and Conservative partisans have accused the website of favouring the Liberals as the project's overseer is Milton Chan, a longtime Liberal activist. In fact, the project under-predicted the Liberals' seat totals in the 2000 federal election and last year's provincial contests in Ontario and Quebec.
In BC, they're predicting 23 Conservatives, 7 NDPers, 5 Liberals, and Independent Chuck Cadman in Surrey North. Liberals are forecast to win in Victoria, Esquimalt, two Vancouver ridings, and Burnaby-New Westminster; the NDP are the choice in the two mid-Island ridings, three Vancouver seats, Svend Robinson's old turf in Burnaby-Douglas, and New Westminster-Coquitlam. EPP forecasts the Conservatives sweeping the rest of the province, although almost completely shut out of the Burrard Peninsula of Vancouver, Burnaby, New Westminster, and the Tri-Cities.
The EPP's methodology is "prediction by submission." Participants ty to guess the winner in individual ridings, backed by whatever information they have at hand. The project's judges weigh each submission, giving more weight to those with a raft of facts to back their assertion and less to ill-informed postings or predictors who show a consistent bias. (If someone's predicting Grits all over the place, even in rural Alberta, chances are they don't get much weight; the same goes for someone calling ridings like York Centre for the Conservatives!) Somehow or other, they come to a conclusion for each riding based on those submissions; safe ridings are predicted early on; the last 80 or so ridings aren't called until a couple of days before the election itself.
You can browse through the website and look at the predictions and submissions for every riding, and judge the both the project and posters for yourself. (Confession: I did make predictions in a handful of local ridings, though I didn't participate during the writ period due to time constraints.)
(Of course, there are literally dozens of candidates who deserve to be elected, but what fun is there in writing about them?)
No wonder I love politics.
As far as the accusations of Chan being partisan by partisan goes, it may be worth remembering that not only does EPP usually underestimate the Grit total, but that Chan worked on the Copps leadership campaign. Hardly likely to be a raving pro-Martinite is he?
I didn't predict in as many ridings as I intended to... but they added by near libel-writ-inducing rant about the Windsor Star's polling methodology to the Windsor-Tecumseh riding, so I'm happy :-)
And here the rant is:
"While I've not seen the Windsor Star poll (so I don't know what outfit did it, or if it was a (aiiieee!!!) University Poll... of for that matter how many people were polled) but the numbers posted here add up to 70%.
Now unless there's been a sudden explosion in the Green vote hereabouts, that means that according to the poll *30%* of the electorate of Windsor-Tecumseh are undecided.
Now a figure like that is (just about) possible in Saskatchewan, but anywhere else it looks as though the company couldn't even be bothered to go through the motions by pressing for leaners (and if leaners are not pressed for, it tends to deflate support for Centre Left parties).
If that's what's happend (as looks likely) the poll isn't worth the paper it's printed on."
Reports, opinions, columns, and anything else on this site, are © 2002-2003 Ian King unless otherwise noted. Permission granted to use material on this site for non-commercial purposes provided that the work is attributed to the original author. All other uses require specific permission of the original author. Contact weblog owner with any inquiries.Feel free to link to this web log. The management likes getting lots of traffic.