Monday, May 26, 2014

EKOS shows sustained Ontario Liberal lead

Friday evening, EKOS Research released their latest poll for iPolitics showing a stable race in Ontario, with the Liberals leading the Progressive Conservatives. This is in contradiction to the previous poll that hit the wires, by Ipsos Reid. But it should be noted that since the campaign officially began (Oracle had a poll out before the writ dropped showing the PCs ahead), Ipsos Reid has been the only pollster to show a PC lead. We're far from consensus (EKOS has a six point edge for the Liberals, Forum had it at seven points, Abacus showed a tie when we last heard from them) but we may be moving towards a higher degree of evidence pointing to a narrow Liberal advantage.

The projection has swung back in favour of the Liberals, with 35.6% support (or between 34% and 39%) against 33.5% for the Tories (or between 32% and 37%). The New Democrats trail at length with 21.8% (or between 20% and 23%), while the Greens jumped to 8.1% (or between 6% and 10%).

In terms of the seats, the Liberals now lead with 48 (or between 41 and 58) and could potentially win a majority, though a minority remains more likely. The PCs sit at 39 (or between 31 and 47), and could still potentially pull off a win with what the polls are showing. The NDP sits at between 16 and 22 seats.

EKOS was last in the field on May 13-15, and since then has recorded no major change in support among the three main parties. The Liberals were down 1.3 points to 35.8%, the PCs were down 0.3 points to 30%, and the NDP was down 0.5 points to 20.4%.

The Greens made a jump of 4.6 points to 11.9%, which is almost certainly a sampling anomaly. EKOS will be releasing likely voter data in their next report, so we can expect the Greens to fall in that regard.

EKOS has been showing very steady numbers in their campaign polling. But the Liberals may not be losing the turnout war anymore. EKOS found that the party had 40% support among Ontarians 65 and older, just ahead of the PCs at 38% (the Tories were ahead by eight points among this group in EKOS's last poll). The Liberals also led among voters aged 45-64.

Regionally, the Liberals held leads in every region except eastern Ontario and the northeastern and central parts of the province (also note that the sample in the Northwest, just 28, has a margin of error of +/- 19 points). The Liberal lead in the southwest is somewhat unusual, but otherwise these numbers are generally what other polls have shown when the Liberals have been in front.

A few regional shifts appear outside the margin of error and are worth noting. But first let's just reiterate that the Green numbers are too high. The party gained 7.7 points in Toronto to hit 10.8%, and gained 12.1 points in eastern Ontario to hit 16.9% - putting them ahead of the NDP. That simply isn't plausible.

Elsewhere, there was a swing between the Liberals and NDP in Toronto. The Liberals dropped 12.7 points to 39.6%, while the NDP gained 9.4 points to reach 23.7%. This seems like more of a reset, as EKOS had abnormally low NDP numbers in the provincial capital last week.

And in the northeast and central part of Ontario, the PCs picked up 15.4 points to reach 34.9% and take the lead.

The polls are still far from clear, as even the polls that give the Liberals the lead hardly agree on the size of that lead. But let's, again, try to make some sense of it.

The chart below shows the polls released so far in the campaign by firms that have reported more than once (including Abacus Data, which has reported just once but will also have new numbers out tonight). Each vertical line represents a day in which a pollster was in the field. So this EKOS poll, for example, has eight lines as it was in the field over eight days. The last Forum poll has one, since it was in the field for a single day. The lines also roughly represent the margin of error for each party in each poll (assuming a probabilistic sample).


It is still rather muddled and not all of the polls overlap, even when taking into account the margin of error and when they were conducted on the same days. But some patterns do seem visible.

The PC results are the easiest to follow, as with the confidence intervals it is possible to run from one end of the chart to the other. The PCs started the campaign high, and have since mostly dropped. The Liberals started the campaign lower, and have since mostly increased. The NDP has been generally stable.

I think something clearer is starting to emerge from this campaign. The Liberals and PCs are in a very close race, but neither have momentum and certainly not the Tories. Nevertheless, if an election were held today - considering turnout implications - the result would still be a toss-up.

39 comments:

  1. Your polling trends and intervals graph is very nice. It does help to give a better sense of how things may be shaking out. Does it look much different if you include the one-off polls?

    With respect to Ekos, it'll be very interesting to see what happens when they start using a "likely voter" filter, since that seems to be the key question for the whole election. It'd be very helpful if they applied their filter to at least one prior set of data (e.g., this release) when they do start releasing it.

    And, what were they thinking, separating out Northwestern from Northeastern and Central Ontario? Why bother? Separating Northern from Central Ontario could make sense (and still have minimally meaningful sample sizes), but this?? I just don't get it.

    ReplyDelete
  2. The heavy weight you accord the most recent poll must be at least partly responsible for the see-saw & confusing changes from poll to poll. (I see the weights from http://1.bp.blogspot.com/-yN3be1r-fCE/U4NBzSPl8rI/AAAAAAAAS-g/TCss9BbfvuE/s1600/Poll+Details.png)

    I'm not a scientist, so I may be clueless, but I don't understand why you don't use a rolling average of the last 3 - 6 polls, weighting them all equally. I believe a method similar to that is used by a similar American site with which you may be familiar: http://www.electoral-vote.com/

    I'm certainly not aware of a scientific reason to weight the most recent poll so heavily, particularly in the face of your own observation of the uncertain validity of IVR polling. I feel a little sea-sick every time your results go topsy-turvy, and just don't see the need.

    ReplyDelete
    Replies
    1. It is because the data is more current. This may not mean much at this point in the campaign, but is vitally important in the last few days. Rather than switch the weighting modelling mid-way through the campaign, I keep it uniform throughout.

      A rolling average that incorporates polls that are too old will not be able to capture changes in voting intentions, as occurred in the 2011 federal election.

      Delete
    2. Ok that answers my comment below...

      Delete
    3. Yes I'm with you there, as seen in my comment below. I come here to compare my projection (as I often do, logically) and I'm always surprised of the huge variations. It's especially the case after a Ipsos or Ekos poll. I think Eric's weighting should be adjusted during the campaign (when we don,t have that many polls). But I understand his logic and why he does it.

      Delete
  3. 12% for the Greens does indeed put a big question mark on this latest EKOS poll.

    ReplyDelete
    Replies
    1. That, or people are so truly disillusioned with what's going on that they are choosing the Green's as a form of 'None of the Above'

      Delete
    2. EKOS themselves said that they don't have a likely voter model yet and they expect the Green number to go down.

      Though really, people should be voting for the Greens considering the other choices.

      Delete
    3. There is a reasonable possibility that left-NDP voters are considering voting Green because they are disatisfied with Howarth's shift to the right... whether they actually end up voting Green is another matter.

      Delete
  4. Any word on polls from Angus Reid or Nanos? Would love to see them weigh in.

    ReplyDelete
    Replies
    1. Nanos better polls this election. If they want to then go on TV and lecture everybody else, the least they can do is actually pol! (see BC when Nik Nanos was explaining was everyone was wrong.. despite the fact he didn't poll lol)

      Delete
    2. I can't stand Nik Nanos on a personal level (nor for that matter Bricker or Graves). It would, however, be nice to see other pollsters in this race, as we keep seeing the same companies releasing more or less the same numbers.

      Delete
  5. 12% for the Greens may or may not be a sampling anomaly in light of the recent adverse comments by well-known progressives about the NDP.

    ReplyDelete
  6. It is an Ekos poll.


    Based on EKOS's recent track record this might be the is 1 time out of 20 that both the Liberals or the Cons will actually be within the 2.8% EKOS advertises as the MOE.

    Mr. Graves has some nice verbiage around this poll seeming to hedge his bets:

    " The angry, regime-fatigued voters are squarely in Progressive Conservative Leader Tim Hudak’s camp, while the pro-activist camp sees Wynne as a more plausible champion."

    If the angry regime change voter are motivated to come out and vote more than last election (say 55%) look for a huge CP majority.

    In 2011 only 49% of Ontario voters were engaged enough to vote.

    I think there would be extreme value in pollsters tracking what they think the turnout will be.

    That would be hard to do as almost all people answering the survey would say they are going to vote, obviously 51% of the sample universe chose not to.

    ReplyDelete
    Replies
    1. " The angry, regime-fatigued voters are squarely in Progressive Conservative Leader Tim Hudak’s camp, while the pro-activist camp sees Wynne as a more plausible champion."

      I disagree. I think there is a strong "fed-up with the Liberals, not willing to touch Hudak" issue that is going on, but Horvath is campaigning so badly it is quite possible the poll is not in error with respect to the Greens.

      Delete
    2. *PC majority

      In Ontario we have the Progressive Conservative party.... not a "CP" as you said!

      I say that fully knowing there is very little about the Progressive Conservative Party of Ontario that is "progressive" this election haha

      Delete
  7. Though I tend to agree that the Greens will not perform to the level indicated, I'm wondering if the certainty which which you assert that their numbers are too high is based on stats or gut or a combination of the two? For example, would you have found the NDP spike (when it first showed up in the polls) in the last federal election equally unlikely to play out, or was there more data to back that up?

    ReplyDelete
    Replies
    1. It is based on experience (Greens are often high in EKOS polling, and almost always over-estimated generally), and the lack of corroborating evidence.

      Delete
  8. Genuine and non-trolling remark Eric, but don't you think your weighting for the polls should be changed, at least during the campaign (you can still heavily weigh the last polls at the end). Because it's really weird how everytime I come to your site, you have a different party leading. I know polls have been volatile, but the average has been stable (unless, as you do, you base your estimates heavily on the last published poll).

    ReplyDelete
  9. Using the poll results, I get:

    54 OLP
    36 PC
    17 NDP

    With the average, I get:

    48 OLP
    41 PC
    18 NDP

    ReplyDelete
  10. How likely is it that the PC's would be down 5 points from 2011? I can understand the NDP maybe being down from 2011 with all the controversy over left-wing NDP members being upset with her drift to the right, but wouldn't the PC vote be up in this election? The indications seem to be that Hudak is running a better campaign than in 2011 and that there is a desire for change in Ontario. Or maybe the pollsters have that wrong?

    ReplyDelete
    Replies
    1. It is possible that pollsters have it wrong, but it's also possible that saying you're going to fire 100 000 people starts to put those job losses in the realm of the personal for a lot of people that are otherwise open to general unspecified cuts and your other messages.

      Delete
    2. And it's not just those 100,000 people. It's their wives, husbands, sisters, brothers, mothers, fathers, children, Grandparents, etc. etc...

      Hudak isn't just threatening those with the jobs, he's poking their loved ones with his trickle-down, corporate-tax cut stick, too.

      My guess, all totalled, we're talking millions of Ontarians.

      Delete
    3. Hudak running a better campaign? Not if you or any of your friends/relatives has any kind of government job (doctor, nurse, teacher, ...).

      Not if you have kids .. increased class size. Huge increase in teacher:student ratio for kindergarten.

      Not if you use transit. Lots of planned transit lines cancelled.

      Not if you live in the north. Apparently being in Peterborough is more important than anywhere in Northern Ontario.

      And today he said he'd privatize public transit!

      It's like he's out to alienate every possible group in the province. He would only have had to tinkered his message slightly to avoid upsetting so many people!

      It's a stunningly inept campaign. The only group he's going to win is his core. But they weren't going to vote for anything else anyways.

      Delete
    4. Hudak's running a better campaign, but I don't think the perception of him as incompetent really solidified until after the election in 2011. Now he has to fight that.

      Delete
  11. Fingers crossed that the Greens are actually showing increased support. I think a Green MPP would definitely bring Ontario a lot of good.

    Is there any way we can find polling for Guelph?

    ReplyDelete
  12. This smells fishy to me. Left-leaning EKOS comes out with another poll with the Libs in the lead, right after right-leaning Ipsos put the Tories in the lead. Is it just me, or is something messed up here? I think a post that outlines the historical bias of these polling companies would be useful.

    ReplyDelete
  13. As a Green running in the Northwest I'd love those figures for up here to be right. I'm in the Thunder Bay-Atikokan riding while the one next to mine is running a PC candidate from Cambridge (about 18 hour drive away) which is going over like a lead balloon. Mix in the former PC candidate coming out as quite anti-First Nations and Hudak not coming here for the debate and I'm sure a lot of PC voters are looking for someone to vote for. The Libs going left of the NDP makes it extra tough on them so I wouldn't be shocked if many come to the Green's for at least one election, especially with the PC's having no more shot that I do of winning here (it could happen, see NDP in Quebec last federal election, but we all know the odds).

    Liberals appear to be winning the 'sign war' but also have by far the most cash on hand. The PC I'm against has put up a lot of signs on public property but not many in yards.

    June 12th will be interesting up here.

    ReplyDelete
  14. Interesting that at the moment the current projection shows almost no change from the legislature at the time of dissolution

    ReplyDelete
  15. As I've been saying for days here it is all about jitter. This only supports that view.

    Hiwever I do predict and increase in Liberal and NDP support as Hudak fades. Skipping the Northern Debate has to be a big fubar !!

    ReplyDelete
    Replies
    1. Not sure how much it will hurt the PC's skipping the debate here. The biggest problem is Hudak didn't get practice for the debate people will pay attention to. As a northerner I hate to say it, but this debate was a 'so what' outside of this area and the PC's never had a shot up here anyways (running flown in candidates, high government employment thus the 100k job cut scares people here more, cancelling the LRT would hurt here too due to them being built here).

      Delete
    2. I think it is already clear that PC support is slipping. All recent polls, including Ipsos and Abacus, indicate that.

      Are people actually surprised though? The PC platform is too extreme. The "Million Jobs" rhetoric is not gaining any traction.

      Of course, the PC base consisting of roughly 1/3 of the province would go to the polls. Not because of Hudak and his platform, but because they want their local PC candidate to be re-elected or they want to see the Liberals gone.

      Delete
    3. There is the funny thing. Hudak didn't need his million jobs, 100k cuts thing to win. He just needed to campaign against the Libs and say 'we wont do that (gas plant, Ornge, etc.). Pound on corruption and rot that comes from being in power too long while being fuzzy on 'efficiency in govt' and 'reduce taxes on individuals once deficit is beaten' 'no new taxes' and he probably would've had it. Instead he made it about his plan which sounds silly on the surface (1 million jobs for 1/2 million jobless is just too easy an area to attack) or too mean spirited (100k job cuts, increasing class sizes which scares every parent as classes seem overcrowded as is).

      How the Tories have lost the last 2 elections and now are poised for the trifecta is beyond me. Those 3 all were perfect setups for a win for them.

      Delete
  16. How the Tories keep blowing it is beyond me. 3 elections in a row they had a perfect setup. All 3 times all they had to do was look reasonable - no major policies beyond 'more efficient, no lies, tax cuts once deficit paid' and they'd have it locked up. Instead 'fund church based schools' ::boom:: 'Harris lite' ::boom:: 'million jobs for 1/2 million jobless, 100k cuts increasing class size' and maybe a 3rd ::boom:: down the polls in very winnable elections.

    If I was a member of that party I'd be extremely mad right now. With the Liberals shooting left of the NDP all the PC's had to do to win was be in the centre and it would've been an easy cakewalk. Instead we'll probably see a Liberal/NDP govt like we've had for the last few years. It is an achievement to find defeat in the jaws of victory 3 times straight. Christine Elliot would've been a better choice - more centre, what most voters want. Instead Harris lite and no power.

    ReplyDelete
    Replies
    1. I agree John except that Hudak is going where Harris didn't. He's not a smart man.

      Delete
    2. The Ontario PC party may be suffering from GOP disease -- anybody that the die-hard core will elect as leader does not suit the center of the general electorate well enough for them to get a bigger share of the swing voters. They will remain in the wilderness of opposition until the old Red Tory gang re-take the party.

      Delete
    3. Yes eg I agree. No longer the party of Bill Davis. Harris saw to that !!

      Delete
  17. Peter what do you mean by Jitter?

    ReplyDelete
    Replies
    1. When there is no clear winner/loser the pollsters number float back and forth. Once you get a five percent or bigger difference then the jitter disappears.

      Delete

COMMENT MODERATION POLICY - Please be respectful when commenting. If choosing to remain anonymous, please sign your comment with some sort of pseudonym to avoid confusion. Please do not use any derogatory terms for fellow commenters, parties, or politicians. Inflammatory and overly partisan comments will not be posted. PLEASE KEEP DISCUSSION ON TOPIC.