Wednesday, May 14, 2014

And the pendulum swings back again

The see-sawing of the polls is causing a bit of whiplash, but we should beware not to get too caught up in how the numbers are changing from one poll to the next. The new poll by Forum Research for the Toronto Star is a good example of that, as they now show the Liberals ahead of the Progressive Conservatives.

The projection has accordingly swung violently back to a tie in the seat count and a near-tie in the vote projection. This is what happens when there are spaces of three days between individual polls being conducted: the weight of the previous poll is automatically reduced by almost three-quarters. That may sound like a lot, but this sort of weighting has proven its worth time and time again.

The PCs continue to hold the lead in voting intentions, however, with 36.5% support (or between 35% and 40%). The Liberals follow closely behind with 35.7% (or between 34% and 39%), while the New Democrats trail in third with 22.4% (or between 21% and 24%).

(As always, you can find the detailed regional breakdowns, riding projections, and tracking charts by clicking on the chart at the top of this page, or clicking here.)

In terms of seats, the PCs and Liberals are back in a tie with 43 apiece, though the Liberal range (36 to 53 seats) is slightly better than the Tories' range (34 to 52 seats). The New Democrats are back to 21 seats, or between 17 and 23.

The Forum poll added to the projection is, again, not without its issues. The sample is just as skewed as it was last week, with 66% of the sample 55 or older and just 6% of it 34 or younger. The appropriate proportions, if this raw sample was representative, would be closer to 36% and 26%, respectively. When Forum increases the weight of the small sample of younger voters (which gave the Liberals a wide lead over the Tories, with the NDP in a distant third), there is the potential that the errors that crept in due to the small sample size become magnified.

There is also the issue with the seat projection that Forum reports: 68 seats for the Liberals, 26 seats for the Tories, and 13 seats for the NDP. In other words, with the results of the election virtually identical to the last one in 2011, the Liberals are able to win 15 more seats, 11 coming from the Tories and four from the NDP. That is simply not plausible.

When I plug Forum's regional numbers into my model - which uses the exact same regional definitions as Forum - I instead get 48 seats for the Liberals, 39 for the Tories, and 20 for the New Democrats. If I was a betting man, I'd most definitely bet that mine would be closer than Forum's. Most observers of Ontario politics would do the same, I'm sure.

But let's look at the poll itself. Forum was last in the field on May 2-3. Since then, the Liberals picked up five points to move into the lead with 38%, with the PCs dropping three points to 35%. The NDP and Greens each slipped one point to 21% and 5%, respectively.

The jump in support for the Liberals is outside the margin of error, which Forum chalks up largely to Tim Hudak's promise to cut 100,000 jobs in the public service. Their poll reported that just 26% of respondents thought that was a good idea.

The Liberals have picked up support in two consecutive Forum polls now, while the New Democrats have dropped in four. That is a trend worth keeping an eye on, though it should be pointed out that Ipsos Reid, for example, has shown the exact opposite and the Innovative Research Group has shown Liberal stability over the same period.

The Tories do seem to have a turnout advantage, but perhaps not to the extent suggested by other recent polls. The PCs were ahead 47% to 34% among voters aged 65 and older, but the Liberals led among voters between the ages of 55 and 64, by a margin of 39% to 35%.

Kathleen Wynne has seen an uptick in her personal approval ratings, jumping four points to 38%. This came primarily from voters who formed an opinion of the Liberal leader, as the number of 'don't knows' fell from 15% to 12%. She was also up four points on who would make the best premier, to 32%.

Hudak's approval rating slipped to 23%, but his disapproval rating soared by eight points to 59%. This was, again, due to a drop in 'don't knows', from 23% to 17%, while 22% of respondents said Hudak would make the best premier (unchanged).

Andrea Horwath's numbers were stable, with an approval rating of 35% and a disapproval rating of 43% (the lowest of the three, below Wynne's 50%). Just 15% said she'd make the best premier.

At the regional level, the Liberals seem to have made significant gains in the 905 area code and the southwestern part of the province. In the 905, the Liberals jumped nine points to 45%, followed by the Tories at 29% (down nine points) and the NDP at 21%. In southwest Ontario, the PCs still led with 39%, but the Liberals were up eight points to 30%. The NDP was in third at 20%.

The Liberals led in Toronto with 39% to 32% for the Tories and 24% for the NDP, while they were narrowly ahead in northern Ontario with 37% to 36% for the PCs and 22% for the NDP.

The Tories led in eastern Ontario with 45%, followed by the Liberals at 36% and the NDP at 15% (down eight points).

With the polls unable to agree on the province wide tally, we really do need to focus on the trends from one poll to the next from the same pollsters. Innovative and Ipsos are, so far, showing stability in the race. Forum is recording a move to the Liberals, in the short term at the expense of the PCs but over the last few months at the expense of the NDP. We will have to see if the other firms corroborate these trends, whether or not they show the same topline numbers. At this point, though, the best we can say is that the race remains a toss-up - primarily because we just don't know any better.

54 comments:

  1. Eric I think in fact what we are seeing here is a trend as distinct from a snapshot. I think we will see a slow decrease in Tory support as the pubic realizes just how devastating Hudak's policies are.

    ReplyDelete
    Replies
    1. Nonsense! This is the exact same thing we have seen happen for months where polls have been showing wild swings between the Liberals and the PCs. Only once we see a clear trend showing a distinct lead across multiple polls for either the Liberals or the Tories will anyone be qualified to say that a trend is forming. To claim anything otherwise displays partisanship rather than rationality. We'll just have to wait and see what happens.

      Delete
    2. ... and just as fast as the pendulum swings one way, so it swing stack the other with another poll showing an increase in PC support since their last poll. So much for that trend against Tim Hudak's policies.

      If anything, all these polls are doing is making things all the more confusing to follow!

      Delete
  2. I normally do not comment on these polls but a Star/Forum poll that show the Liberals in such a lead is a bit questionable. Following The Star's election reporting is a bit like following the Liberals themselves. I would like to see the methodology employed and the questions put to the sample. I do know that I was surveyed last week by Forum (I presume) and the poll was clearly skewed in terms of how the questions were put and where the parties were placed in terms of questioning i.e.. Liberals 1, Conservatives 2, NDP 3, "Other (I believe) 4. That said, the statement re: trends is significant. I await Nanos, Ekos and if I could see a Polaris poll (which I suspect the Liberals are using) I would be even more satisfied.

    ReplyDelete
    Replies
    1. Pollsters randomize the order, so while you would have gotten that order of parties, another respondents would have gotten the Conservatives first, while another would have gotten the NDP, etc.

      Delete
    2. Does Forum's robopolls have the capability of randomizing questions? Most autodial systems that I know of don't.

      Delete
    3. Curious Eric. Why would pollsters randomize this order, when they could probably balance it over such a large sample size? I suppose, in a sense I'm answering my own question. With large samples, I guess it's likely to balance itself out. But, there's no guarantee.

      Delete
    4. If they balanced it systematically (as opposed to randomly) they might introduce a bias into the results.

      Delete
  3. I think these polls emphasize that the electorate is not really focused on the election yet.

    The parties themselves seem somewhat disorganized. Silly gaffes from all three parties. The Liberals and NDP have not even nominated their full slate of candidates yet.

    A slow start to a rather long election. We got about 30 days left of this.

    The election was regarded by analysts as one that would be hard to predict, and it is living up to its name.

    ReplyDelete
  4. Some reports, such as this one, claim that the poll actually showed the Tories with 33%, not 35%:
    http://www.bramptonguardian.com/news-story/4517677-hudak-s-popularity-takes-a-hit-over-jobs-plan/
    Which number is accurate?

    ReplyDelete
    Replies
    1. I have the Forum report, it is 35%.

      Delete
  5. Using the Forum numbers, I get:

    52 OLP
    39 PC
    16 NDP

    With the aggregated numbers, it gives me:

    45 PC
    44 OLP
    18 NDP

    Very interesting race right now. I'm really wondering how this will end (I don't know why, but I have a feeling we'll have a BC/Alberta major swing on election night and an unpredictable majority will get elected).

    ReplyDelete
  6. Green-Marxist-Libertarian coalition government for sure.

    ReplyDelete
  7. I really believe that the 100 000 job cut policy plays out badly for Hudak. I live in a rural/conservative neighborhood in a southwestern Ontario riding and in this immediate area people mostly vote conservative or abstain. The riding is currently represented to Liberal Ted McMeekin who won by a few thousand votes in 2011 mainly due to the inclusion of Hamilton west and parts of Dundas in the riding. This southwestern Ontario riding is one of the PC target ridings that Hudak must take if he wants to win. Since this comment was made I've heard die-hard conservatives say they will never vote for Hudak, despite having no love for the other parties. I think going forward this is going to lead to more of a turnout issue which is usually an advantage for the PC's. I cannot prove this with data making it only an opinion probably not worthy of posting on a stats page such as this one, but that is my take. However I do think its helpful to get a feeling of what is happening on the ground in addition to polling. I am really starting to think the PC's have shot their bolt and lost another winnable election as in 2011.

    ReplyDelete
    Replies
    1. The fiscal reality is Ontario is broke! The deficit was $36 billion last year-5.5% of GDP! Debt rose 14%! Since the Liberals came to office the debt has doubled and then some! Unfortunately, the Liberals sat on their haunches for the last decade and instead of saving during the good times they over-spent. Once people realise there is no other choice but, cut civil servants they'll come to their senses. A large share of government expenditure is salaries. You can't cut spending without reducing labour costs-it really is that simple. The alternative of course is to let our children and grandchildren pay for our luxuries, that is just plain selfish.

      Nobody where I live thinks the Liberals have the best interest of anyone other than the Liberal party at heart. They long ago used up the good faith people used to bestow them with. It has come to the point that long time Liberals are likely to vote NDP simply to send a message. Most people I know whatever their political stripe are simply embarrassed and saddened that the Liberal-old Boys and Bay St. Club has ruined the career of such a amiable lady as Kathleen Wynne.

      Fool me once shame on you, fool me twice shame on me-I hope Ontarians realise the dire straits they are in. At this rate Ontarians won't need Hudak to implement job cuts the private sector and the recession that still has a firm grip on Ontario will cause economic contraction.

      Delete
    2. As a BC resident, so not current on Ontario politics, when I look at the Ontario Ministry of Finance's site I see a deficit of just under $12B ( http://www.fin.gov.on.ca/en/budget/fallstatement/2013/chapter3b.html ). There was a $19B deficit in 2009-10, at the height of the world financial crisis (that's the fault of the Ontario provincial government?), but the Liberals cut that to $9B in 2012-13 before it went up again a bit this year. It's still higher than it should be, but it's nowhere near the insanity that the $36B described by Carbonear Pete would be and it doesn't seem like the Liberals are ignoring it.

      I find Mr. Hudak's talk of "hard decisions" distasteful. It's a "hard decision" to lay off public servants, says the guy who's spent his career in the Smaller Government Party. Is he expecting us to take this seriously? This is in no way a "hard decision" for him. He says he has to do this because of the deficit, but he can still afford to reduce corporate taxes, a policy that will increase the deficit, and will be "hard" on exactly *none* of his supporters. Somehow this will increase the size of Ontario's economy by over 10%, but how? It won't make any business that's making a loss profitable. It would increase the (post-interest) RoI of new projects by a fraction of a percent, but are there really so many new projects that are thought profitable but a smidgeon short of being profitable enough to go ahead that they will increase the size of Ontario's economy by over 10%? If I were in charge of cutting Ontario's taxes in such a way as to increase jobs, I'd cut Ontario's employer-paid payroll tax (the Employer Health Tax - for comparison, none of the provinces west of Manitoba have provincial employer-paid payroll taxes), or perhaps give employers a refundable tax credit for money spent on the employer's share of CPP and EI payments, either of which would make labour cheaper for Ontario businesses, but Mr. Hudak's rather pointedly (from my point of view) not proposing that. Instead he's proposing to cut taxes in a way that will benefit stockholders exclusively. And the guy whose party's support is disproportionately from seniors is willing to make the "hard decision" to cut teachers (primary and secondary education are 19% of the Ontario budget), but not the 38% of provincial expenditures that goes on health care that principally benefits... seniors. So, so far, all of Hudak's "hard decisions" have only been hard on people he never expected to support him.

      Oh, and school districts are bureaucracies. You might want to check the fine print before you assume that merging two bureaucracies will give you a smaller, cheaper, bureaucracy. I don't know about the Ontario proposal, but I do know that some politicians who have merged school boards before, predicting economies of scale, have wound up with school boards that cost more than the sum of the smaller pre-merge school boards.

      Delete
    3. Michael,

      They separate the operating deficit 12 B and the capital deficit-that explains why debt rose by 36 billion in 2013-14. The fact remains if debt rises by 36 billion per year that in effect is the deficit since, expenditures both operating and capital were 36 billion more than revenue.

      Christy has the same newfangled accounting in BC-it is deceptive and purposefully meant to be so.

      Delete
  8. Could we get a seat count based on this Forum poll alone? Anyone good with seat projections who could do this?
    TIA

    ReplyDelete
    Replies
    1. You've hurt my feelings. I did do a seat count based on the Forum poll in my post above, the last paragraph before the Forum chart.

      Delete
    2. My apologies Eric. Found it. Thanks!

      Delete
    3. I also posted a seat-count from my model in the comments, it went:

      52 OLP
      39 PC
      16 NDP

      Delete
  9. Piece on the CBC website on just how bad this 100,000 cut will be for education. Last thing any parent wants is bigger classes but that's Hudak's intent.

    ReplyDelete
    Replies
    1. With the province headed toward complete fiscal ruin it's not a question of if cuts like this will happen, but when and under who. Anyone who thinks otherwise is the very definition of the word naive. Hudak, so far, is the only one who so far has the fortitude to share the hard truth with people no matter how badly they might not like to hear it. The debates are going to be very interesting to watch to see how well each party leader can articulate their position on this very serious issue the province is facing.

      Delete
    2. Peter,

      Ontario can't afford their education system any more. Of course all parents want small class sizes but, do they also want to leave their children with crippling debt? The way things are going the rating agencies will soon force Ontario to cut services. Rising debt servicing costs will decrease available revenue to fund programs such as education. The debt is headed towards 80% of GDP in the next 6-7 years.

      Most Ontarians realize they can ill afford another Liberal government.

      Delete
    3. Ontario can't afford Junior Kindergarten and full day Kindergarten. Nor can it afford the luxury of two school systems. Amalgamating the Separate and Public systems would save in excess of one billion dollars per year. Going back to half day kindergarten would save close two billion dollars. Those are changes that would benefit everyone.

      Delete
    4. I love these Malthusian (or Scroogeian, if you prefer) arguments. "Can't afford their education system"? Let's cut to the chase and simply get rid of the surplus population...

      Delete
    5. chirumenga,

      What pejorative terms you choose to use. In fact we know Scrooge is capable of change when presented with facts and the outcome of his choices. Thus far, Liberals and Dippers have not shown such enlightenment.

      In fact a decrease in population (one wonders what you mean by "surplus population"-scary) would not solve the problem since a population decrease would increase the per capita debt. In short your idea would make the situation worse.

      Ontarians need to confront the problem-ignoring the situation will only make matters worse. I find it truly shocking and frankly mean spirited that a large segment of Ontarians wish to make their children's future less prosperous so they may have a better standard of living today, perhaps a new flat screen for every family!
      It is plain inter-generational greed. As I wrote before Ontario has a choice; confront their fiscal imbalance today or have the rating agencies or increasing debt servicing costs mandate expenditure cuts in the near future.

      Delete
    6. Chim you have to love the way the "believers" only see cutting costs whereas most parents want the Best Possible Education and damn the cost for their kids !!

      Delete
    7. Peter you are not qualified to speak unilaterally on what parent expect from public education any more than I or anyone else are qualified to speak unilaterally on parents not wanting their children to inherit a bankrupt province.

      Delete
    8. Parents want the best for their children. Get used to it.

      Delete
    9. Peter,

      Most parents realize education is important but, so are jobs and economic opportunity. We know correlations exist between family income and education attainment and between well fed kids and educational attainment. Impoverishing families will not allow for children to receive a better education. Allowing parents to work meaningful well-paying jobs will allow for better educated kids.

      You say parents want the best education and damn the cost but, how many parents want to in-debt their children? Most likely none.

      The Ontario economy grew at 1.2% last year-that is anemic growth probably below the growth in population so under the Liberal-NDP unholy alliance Ontarians became less well off. Everyone wants their kids to have a good education but, if there are no jobs to go into once they graduate that education and the cost borne by Ontario tax payers will have been for naught.

      Delete
    10. Carbonear Pete,

      I'm surprised you find my use of the terms Malthusian and Scroogeian "pejorative". They're descriptive. Anyone willing to sacrifice 100,000 people (and their families) is operating with Malthusian logic - or, at least, with Scrooge's logic. It was Scrooge who referred to "the surplus population" (channelling Malthus) :

      "2nd Portly Gentleman: Many would rather die than go there. [i.e. the poor houses]

      Scrooge: If they'd rather die, then they had better do it and decrease the surplus population."

      And that is the logical extension of Hudak's promises. Cut revenue (i.e. corporate and wealth taxes), cut education and health care, while privatising them as much as possible, and you'll end up with an impoverished population. I agree, the Liberals and NDP (under Rae) promulgated this, but none more so than Harris/Eves, and it would be disingenuous to claim otherwise. The Conservatives proclaim these sorts of policies, the Liberals promote them while claiming otherwise, and the NDP attack them in opposition and adopt them as "necessary evils" when in power. Sorry for my use of "scare tactics" - how impolite. But we've had neo-liberal policies in place - regardless of the party in power - for the last 35 years and we're all worse off (just look at the stats on real income and wealth over that time) while a very few have profitted enormously.

      Delete
    11. Finally the truth emerges: Chirumenga is the re-incarnation of Charles Dickens!

      How else could someone proclaim without documented evidence "Scrooge's logic"

      I am so happy that after 144 years of death the Good Lord has decided to place you on the Earth once more!

      Delete
  10. Looks like Ontario desperately needs one of those 6000+ IVR sample polls, with not less than 50 responses in any riding, before we're going to have any sense of what's going on. Standard sample sizes clearly don't have the power to sort this one out.

    Now, if Hudak's next self-inflicted implosion could just hurry up working its way through the electorate, that would help make the polling much clearer ... :-)

    ReplyDelete
    Replies
    1. You raise a good point. My impression is that sample sizes (generally) haven't risen much in 30 or 40 years (as long as I can remember), yet the population has risen considerably. Éric, are polling samples less representative than they were 20+ years ago?

      Delete
    2. In terms of population growth? It makes no statistical difference if you're polling 1 million or 100 million people, a sample of 1,000 should do the job (within 3%, etc.).

      Now are they less representative than 20 years ago for other reasons? Possibly - it is harder to reach people than it was then. And that is why a sample of 6,000 won't necessarily solve our problems. If the methods used have sampling issues, it won't matter if you sample 1,000 or 10,000 people. Those issues will remain.

      Delete
    3. @chimurenga, as Eric notes, sample sizes have nothing to do with population sizes. The properties of a random sample are fixed, regardless of the size of the population sampled. And, the problems with a non-random sample cannot be fixed by increasing sample size.

      The difficulty that can be fixed by increased sample size is the degree of sampling error - how many percentage points a poll is "accurate to, 19 times out of 20". Recent polls, often with fewer than 1000 respondents, contain sufficient sampling error that we can't say with any confidence which party is leading. We can't make out the signal for the noise. There are only two fixes for that: a stronger signal (greater differences between the parties' support) or less noise (larger samples).

      Delete
    4. A larger poll would be helpful in terms of the regional breakdowns, however, since those samples would be larger and more usable.

      Delete
    5. Thanks for the clarifications. But is the difference between of sample of 10,000 and 1000 less meaningful (statistically speaking) than between 1000 and 500?

      Delete
    6. A sample of 10,000 would have a margin of error of +/- 1%, compared to +/- 3.1% for a sample of 1,000. A sample of 500 has a margin of error of +/- 4.4%.

      It is definitely diminishing returns the larger it gets. Sampling 500 more people cut the MOE by 1.3 points. Sampling a further 9,000 more cut it by just two.

      Delete
    7. New CTV/ Ipsos poll:

      The CP24/CTV Ipsos Reid poll of 801 Ontarians has determined that 39 per cent of decided voters support Tim Hudak’s PC party compared to 30 per cent for Kathleen Wynne’s Liberal party, 24 per cent for Andrea Horwath’s New Democrats and seven per cent for the Green Party/Other.

      Delete
    8. I probably should have paid more attention during the statistics portions of Math 30...

      Thanks, Éric. That's much clearer to me.

      Delete
  11. I should say IVR instead of autodialer.

    ReplyDelete
  12. New IR poll out. PC's have 9 point lead:

    http://www.cp24.com/news/2014-ontario-provincial-election/poll-tories-build-on-lead-make-inroads-in-toronto-1.1822099

    ReplyDelete
    Replies
    1. Only the debates can save the Liberals now. Hudak looked surprisingly polished on TVO's The Agenda tonight.

      Delete
    2. That gives me:

      49 PC
      38 OLP
      20 NDP

      Delete
    3. Really? I watched the same show, and his answers didn't make much sense. He couldn't answer why he thinks heavy corporate tax cuts (which will increase Ontario's deficit) would create more jobs when both the federal Conservatives and the provincial Liberals tried the same thing over the past years, but it didn't lead to more jobs. Even the late Flaherty complained about how companies weren't hiring but were just sitting on their money.

      The host asked him about why Hudak thought doing more of the same thing would work this time, and Hudak just said that he believes it will. As far as I can tell, it appears to be a point of faith with him.

      Plus the Green Party panelist they had afterwards had a good point about how there are under 600,000 unemployed in Ontario, so where would Hudak's "1 million jobs" come from? Seems to me like Hudak just likes easy-to-remember numbers, which makes me suspect that he's not great at math.

      They might've also mentioned that firing 100,000 public servants actually is a bit over 1/6th of those who work for the province (not 10% as is often mentioned), because nearly half of the "public" workers in Ontario actually work for other levels of government. Globe and Mail had a good article about the breakdowns recently:
      http://www.theglobeandmail.com/globe-debate/editorials/can-tim-hudak-win-election-by-100000-job-cuts/article18629579/

      Delete
    4. I did say "polished" but not necessarily persuasive. Like all politicians, he only answered questions he wished he was asked. And I agree, the corporate tax cut is questionable. I think Hudak needs to do more work to make the case that these deep cuts are the best way to go. He hasn't convinced me yet.

      Delete
  13. In a poll where just 6% of the sample of adults is 34 or younger, I'd presume that that 6% is a biased sample of that population unless there's concrete evidence suggesting it's unbiased. In that case the statistical margin of error of an unbiased sample of that size is irrelevant. Do the pollsters give demographic data of that 6% that we can compare to the known properties of that age group as a whole?

    ReplyDelete
  14. This comment has been removed by the author.

    ReplyDelete
  15. Amazing that that Ipsos Reid poll (May 12-14) includes the controversial promise to cut of public sector jobs. I had wondered if the Tories had lost their marbles but their internal polling was probably correct. They needed to take control the agenda. Looks like Premier Hudak now...

    ReplyDelete
    Replies
    1. Notice that the likely voter numbers actually tightened in the new Ipsos poll though.

      Delete
    2. Looks like Premier Hudak one day. Looks like Premier Wynne the another day.

      Still too early to come to conclusions.

      I don't think their controversial plan to cut public sector jobs will sink into voters for another week or two.

      Usually a long election campaign should favour the opposition parties, but I feel this long campaign will favour the Liberals. I find it difficult that Hudak can sustain momentum when he is bound to be analyzed and attacked by the Liberals, NDP, interest groups and the press.

      Delete
    3. The analysis will be equally as detailed for the Liberals and the inevitable question posed will be: after their less than stellar governance do they deserve another mandate?

      During campaigns the Government is always under scrutiny if for nothing more than a reference point. Unfortunately for the Liberals even this reference point has a negative connotation

      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.