Monday, April 04, 2011

Updated Seat Projections

Despite some mid-week adventures by Nanos, the poll numbers stayed relatively flat in Week 1 of the campaign. In effect, outside of our daily dose of Nik, there wasn't a lot to report on until Ekos and Leger rolled in over the weekend. (We also got new numbers from Decima today, but only after I ran my seat projections)

The end result, is a vote line as flat as Saskatchewan.

As a bit of context, the graph above gives a daily popular vote average from on all publicly released polls, based on:

-How recently the polls were conducted. Each poll is given a one-week half-life which meaning a poll released today is worth twice as much as one released a week ago. I consider a poll "added" to the sample on the mean day it was in field (i.e. night 2 of a 3 night field).
-Poll sample sizes
-The accuracy of each company's election polls over the past 5 years

From this, I ran my seat projection model. For the lengthy methodology, click here. The key thing to keep in mind is this model simulates the election 10,000 times in every riding - in each simulation, I include 3 sources of variance:

1) The variance between regional shifts and riding shifts observed in the 2004, 2006, and 2008 elections (i.e. if the Liberals are up 5 points in Ontario, how can we expect their vote to swing in a given riding?)
2) Sample variance, based on the sample size of the polls being used
3) "Pollster variance", based on how much polls have missed the mark in recent campaigns, beyond the sample variance

The model also takes by elections and incumbency into account. And unlike other models, it includes not only the 2008 election as the baseline, but some 2004 and 2006 election results, as well as a riding projection based on demographics. This helps "smooth" out anomalous results from the 2008 campaign, to ensure we don't project the Greens winning Central Nova or anything like that.

What I want to stress is that this model is completely data-driven. At no point have I "tweaked" the results, or given boosts to individual candidates. Once you start doing that, you might as well just consult the Election Prediction Project.

Also, when calculating variance numbers, by election effects, and incumbency effects, the numbers I'm using are based 100% on research I've conducted (using 2004 and 2006 data to simulate the 2008 election). No factor (outside of the 7-day polling half life) has been arbitrarily picked.

OK - I guess that short explanation turned into a long one. I'll keep it brief on further updates. One final disclaimer - this is not a prediction of how the election will turn out. It's based on the poll numbers released as of today...poll numbers that reflect a relatively unengaged electorate.

And with that, here's what's projected:

Based on the simulations, Harper sits at a 56.5% chance of a majority.

Mind you, this actually reflects a drop in support from him from my final pre-election simulation, which pegged him at between 148 to 178 seats. So the gap did narrow a bit in week 1, but it's still a big gap.

Then, as now, Harper's gains have come almost exclusively in Ontario. The lower end of that 95% confidence interval for Ontario is 51 seats - that's the toal he got last election, and he could gain up to 19 more. In every other province, Harper's expect seat total is within 1 or 2 of his total last election.

Again, it's too early to consider this anything more than a fun statistical exercise. But, based on these numbers, it's a lot more fun for Conservatives than Liberals.


  • Given this is a short campaign, and we're already into week 2, I wouldn't say it's early at all. Especially not when you take into account that the early voting takes place in less than 3 weeks if I'm not mistaken.

    By Anonymous ck, at 11:12 p.m.  

  • No way the Liberals would triggered this election if things were truly that bleak for them.

    The Liberals' shrewdness is unmatched. They know how to win elections. Just wait, because when things move, they'll move swiftly.

    By Blogger Robert Vollman, at 11:46 p.m.  

  • Very impressive Dan, nice work!

    By Anonymous Mike, at 11:48 p.m.  

  • Nice piece of work.. Though I do get a sence Canadians are looking for an issue to capture their imagination (how's that for scientific?) That could spur a bump.. So far, I think that so-called "issues" like shady past advisors, whether someone's family was wealthier than they suggest, or how many questions reporters get to ask are just seen as irritants.. The public wants to see some prudent leadership - and the Cons are offering the closest thing.. We're just not sure it's the real thing.

    As I blogged today I would love to see any party say, "This is our plan, but we are uncertain regarding these factors.."

    By Blogger Robert G. Harvie, Q.C., at 11:58 p.m.  

  • Dan, nice work. Maybe after you kick Eric Grenier's behind on election day the Globe and Mail will give you a column.

    Robert, I am inclined to agree. The Liberals must have some dirt on the Tories they have yet to release.

    By Anonymous hosertohoosier, at 12:02 a.m.  

  • ck - Next week is the big week with the debates. If these numbers persist by next Friday, then it's time to panic.

    By Blogger calgarygrit, at 10:46 a.m.  

  • Tory safe seats: 120
    Grit seats-in-play: 106


    By Blogger Robert Vollman, at 12:03 p.m.  

  • Exactly. If Ignatieff has a stellar campaign and all the stars align, the Liberals will win 80 seats, max. I've been trying to post that reality check on Kinsella's bog but of course the comment never gets published.

    By Anonymous Anonymous, at 1:22 p.m.  

  • Another thing. All the polls, even those with the closest margins still show the Conservatives in the high high thirties. Since the big two Canadian parties historically do better at ballot box than in the polls, that still gives Harper his majority, no matter how high the Lib vote is.

    Given that, and the regional focus of Harper's campaign to get the seats he needs, I'd give him his majority.

    Also the Lib numbers have probably been given a bump from the platform release. We'll see if even those hold.

    By Anonymous Anonymous, at 1:26 p.m.  

  • "Tory safe seats: 120
    Grit seats-in-play: 106"

    I'm guessing those numbers mean:
    77 current Liberal seats
    23 (143-120) marginal Tory seats
    6 NDP or Bloc Seats

    As for 80 seats being some sort of cap for the Liberals - that is completely off base. That presumes that Ignatieff will get the same result Dion did, which is not supported by the data.

    Nanos just had the Liberals take the lead in Ontario, while Ignatieff's personal numbers have jumped considerably. Harris-Decima has the Tory-Liberal gap down to 7 points (in 2006 a 6 point deficit for the Liberals translated to 100 seats).

    Its odd - just two similar elections and we decide that elections never change anything. This, even though nearly half of elections have results that would not have been predicted early on (eg. 2006, 1993, 1984, 1974, 1958).

    Campaigns don't matter, fundamentals do. However, fundamentals change. Voter information about fundamentals change in elections. The notion that the more people get to know Michael Ignatieff, the more they like him is not an unreasonable one. Also, each leader has a breaking point at which they will "pull the goalie" in search of a game-changer (eg. the face ad, soldiers with guns). Nothing ever changes - except for when it does.

    By Blogger french wedding cat, at 3:39 p.m.  

  • Sorry, I should have clarified. "Safe seat" is just a seat the party is projected to win by over 10 points. "In play" is a seat they're within 10 points of taking.

    Those numbers will change as the polls change. The Liberals could certainly win 120 or 130 seats if their poll numbers spiked up.

    By Blogger calgarygrit, at 5:02 p.m.  

  • I think the commanding lead at the start of the "You had an option sir!" election was about the same as in this one, no?

    Sad to see Lizzie out of the debates, but it just makes it harder for Harper to look like the poor picked on kid.

    Let's see, the Liberals held 77 seats with a leader who had a hearing problem, spoke poor English, and was not supported by half the party. Now with none of those problems, plus the Harperites demonstrating their contempt for Canadians pretty much every day, I think the debates will be the knockout blow.

    By Anonymous liberal supporter, at 6:21 p.m.  

  • The only ones who WANT a majority government are the parties and the media. So they can pursue their secret agendas unwatched. The people of Canada seem happy with the three of them working together as a minorities. I was happy that Harper spoke to Duceppe about his true purpose, to destroy Canada. Why is he even there at all?

    By Blogger Caterwauler, at 3:24 p.m.  

Post a Comment

<< Home