Canadian election 2010/2011 (user search)
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
June 18, 2024, 10:21:11 AM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Other Elections - Analysis and Discussion
  International Elections (Moderators: afleitch, Hash)
  Canadian election 2010/2011 (search mode)
Pages: [1]
Author Topic: Canadian election 2010/2011  (Read 8277 times)
cinyc
Atlas Icon
*****
Posts: 12,720


« on: June 08, 2010, 01:11:53 AM »

For some reason I get this urge to laugh whenever I read the words 'Angus Reid'.

While Angus Reid was a joke in the UK election, in Canada they have a much better record. They came closest to the final results in the Oct. '08 election and they were the only polling company that correctly showed a close race in the last BC election when everyone else was showing a BC Lib double digit lead.

Did Angus Reid even poll the October '08 election in October?  This website only shows a September Angus Reid Poll.  Nodice.ca seems like it's no dice any more.

I've always thought SES Research (now Nanos Research) was the best Canadian pollster.  They and Ekos more or less nailed the final 2008 result, save for overstating Green and NDP support to the detriment of the Tories.  SES was spot on in 2006.
Logged
cinyc
Atlas Icon
*****
Posts: 12,720


« Reply #1 on: June 22, 2010, 12:22:36 AM »
« Edited: June 22, 2010, 12:24:49 AM by cinyc »

The Greenies outpolled the NDP like 13-12 in a poll in 2008 or so (not campaign season) and an hilarious case of poll sampling fail had the Greenies, while at 9-10% nationally, posting a lead in Quebec.

In another case of sampling fail by EKOS, which seems to be the worst pollster these days, those idiots added a subsample for Ottawa, Montreal, Toronto and Vancouver in their polls. I recommend tracking the Ottawa subsample for particular fun!

The MOEs for the provincial/regional subsamples (except Ontario, in some polls) are almost always so high that they make the subsample results laughably meaningless.  I can only imagine how laughably high the MoE for the Ottawa, Montreal and Vancouver subsamples must be.  Unless EKOS deliberately oversampled those cities, it has to be at least 8-9% if not in the double digits.  The MoE for the Toronto subsample might be a little more reasonable, depending on what EKOS views as Toronto.  
Logged
Pages: [1]  
Jump to:  


Login with username, password and session length

Terms of Service - DMCA Agent and Policy - Privacy Policy and Cookies

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

Page created in 0.02 seconds with 12 queries.