Tuesday, July 22, 2014

Summer hiatus

We're in the dog days of summer now and, as we all know, polls are for dogs. So ThreeHundredEight.com will be taking a brief summer hiatus, returning after the civic holiday long weekend.

In the meantime, you might want to check out some of the recent articles posted to this site that you may have missed:

- A look at how the Ontario provincial election campaign would have been perceived differently if the likely voter models that performed so poorly had been ignored.
- A breakdown of federal party support by age and gender, and an investigation of how this support has shifted since the 2011 federal election.
- A history of the riding of Kingston and the Islands, from John A. Macdonald to Ted Hsu.
- All the latest polls from the upcoming Toronto mayoral race.

And if you really need a polling fix, time to finally check out Tapping into the Pulse, my ebook retrospective of 2013's year in politics and polling. What happened with the polls in British Columbia and the Brandon-Souris by-election? Why were the polls so much better in Nova Scotia? What was Justin Trudeau's first year as Liberal leader like, or the last year before the Quebec and Ontario provincial elections? You can find the links to order here.

You might want to explore the site a little bit as well. After six years and almost 1,500 posts, there is plenty to keep you occupied!

See you in August! Elections in New Brunswick and Toronto are just around the corner - it should be an interesting autumn.

Friday, July 18, 2014

The alternate and truer history of the Ontario provincial election

The conventional wisdom is that the polls did not do a very good job of predicting the result of the Ontario provincial election last month. But that is not entirely true. The likely voter models did a very poor job of estimating what the result would be. The polls of all eligible voters - the numbers that in the past have been the only ones reported - did a decent job.

But how did those likely voter polls influence the narrative of the campaign? What was their role in creating the surprise of election night?

To answer these questions, I re-ran my projection model for the entirety of the election without using likely voter numbers. At the time, I had favoured likely voter results when they were available. This time, I've used only the eligible voter numbers. The chart below shows how the two projections would have stacked up against one another. (Note that throughout this post, the dates refer to the final day of polling that would have been included in the model, rather than the date of publishing.)

 It makes for quite a different story. The difference would have been felt as early as May 9, when the first Ipsos Reid likely voter poll was published. Instead of the wide lead the Tories would have been given - one that they would hold until May 16, the PCs would have been given a narrow lead of just under four points. They would have lost that lead as soon as May 12, regaining it again on May 14, and then losing it - never to have it again - on May 15.

That is quite a different story than the one the likely voter polls told. Instead of relinquishing the lead for good on May 15, the Tories had been awarded the lead for the first three weeks of the campaign. They were given the lead again, though briefly, on May 21, May 27, May 29, and were tied with the Liberals on June 6. But according to the aggregate of the eligible voter polls, the PCs never held the lead in the last four weeks of the campaign.

It is interesting to note that the proposed plan to cut 100,000 jobs, which has been credited as the key moment that cost Tim Hudak the election, was announced on May 9, only a few days before the PCs irrevocably lost the lead.

So instead of a yo-yoing, too-close-to-call campaign, the Liberals would have been considered to be in a good position from mid-May straight through to election day. The Liberal lead would not have been large, but with the exception of the post-debate period, the PCs would never have been pegged to have more than 34.9% support after May 14, with the Liberals never below 35.3% after May 16.

The tightening that occurred after the debate (the news about the police interviewing Dalton McGuinty might have had more of an impact) would have still been recorded in the eligible voter polls, but instead of the close race persisting in the last days, the Liberals would have moved comfortably ahead again on June 9.

That the Liberals took 38.7% of the vote would have still been a bit of a surprise, as the aggregate would have never given the party more than 37.8% of the vote, except on May 20. But the PC fall to just 31.3% would not have been too much of a surprise. Over the last three days of polling, the PCs were steadily falling, from 35.4% on June 9 to 33.8% on June 10 and finally 33.1% on June 11. From there, the drop of 1.8 points is easily explained.

Instead, the PCs were pegged to be far higher. Dropping, yes, from 39.2% on June 8 to 36.9% on June 11, but that is a far cry from the 31.3% they achieved on election night. We were expecting a close race. If we had been ignoring the likely voter numbers, we would have expected a Liberal victory - the only question being whether it would have been a minority or a majority (the projection would have had a likely range of 46 to 56 seats for the OLP).

The New Democrats were, for the most part, under-scored throughout the campaign due to the likely voter models. The difference was negligible to the end of May, but afterwards the effect was more significant. The trend lines would have been mostly the same, with the New Democrats dropping steadily from May 31 to June 5, but a big jump would have been recorded from June 5 to June 7, instead of the slump that the likely voter models suggested.

From June 4 to June 9, the likely voter model aggregate pegged the NDP to be under 20% support, bottoming out at 17.6% on June 8. Without those models, the projection would have only once put the party under 20% (on June 5). For the vast majority of the campaign, the New Democrats would have been estimated to within a few points of their final result. The performance of the eligible voter polls, the aggregate at least, would have been right on the mark on election night: 23.9% instead of the actual 23.8%.

Going forward, I intend to focus primarily on the eligible voter numbers in order to try to tell the story of what the polls are saying is the current state of opinion, rather than what the pollsters are guessing will happen. That is what these likely voter models are in the end, a guess, as no one can estimate with certainty how humans will behave in the future. The huge variation in approaches that each pollster took was testament to that.

I will be recording the results of these models in future elections to provide a bit of a clue to readers as to how turnout might look, but will be keeping the focus on the main numbers reported by the polls until it is proven with consistency that these models will work in Canada. In the Ontario election, the likely voter models were more misleading than informative. This time, a look at the eligible voter polls, like the one above, seems to have told the story more truthfully.

Wednesday, July 16, 2014

Party support by age and gender

The polls currently suggest that the Liberals enjoy a small lead over the Conservatives nationwide, with the New Democrats running in third place. But when the Canadian population is broken down by age and gender, a different story can be told - including how the political mood has shifted since 2011.

During the Kickstarter campaign at the end of 2013, one of the backer rewards was the option to choose a topic of analysis I would look at here. The first request I received, from Keith Neuman of the Environics Institute, was to take a look at federal support broken down by demographics. This is that analysis.

Before getting to it, a few words about the project behind this analysis. Tapping into the Pulse: Political public opinion polling in Canada, 2013 was published as an ebook earlier this year, and is a retrospective look at politics and polling in 2013. The ebook is listed at $4.99, and can be downloaded directly from GumroadAmazon (for your Kindle) and Kobo (for your Kobo eReader).

To give this exercise some context, it would be useful to know how Canadians voted in 2011 by their demographic profile. There are ways to estimate this, such as exit polling or post-election polling, but it is impossible to know with certainty how exactly Canadian demographic groups voted in the last election.

I decided to look at the post-election polling conducted by Abacus Data. From May 2011, just after the election had been held, to August 2011, Abacus Data conducted three polls on federal voting intentions. The numbers matched up quite closely to the 2011 federal election result: an average of 39.6% for the Conservatives (exactly on the mark), 32.2% for the NDP (+1.6), 17.2% for the Liberals (-1.7), and 5.3% for the Greens (+1.4).

Using these three polls, and adjusting for the discrepancy between the election results and the polling numbers, we can get a good idea of how Canadians voted in the last election according to their age and gender.

Not all pollsters release full demographic information, and few use the same age brackets. So to compare voting intentions today to the last election, I've again focused on three polls from Abacus Data (in order to get a large enough sample with which to work). These polls were conducted between January and July 2014. That is a long period of time, but the numbers in Abacus's polling were consistent and, overall, there has been little movement in the polls in 2014.

The Liberals averaged 34% in those three polls, against 29% for the Conservatives, 23.3% for the NDP, and 6.3% for the Greens.

Now that we have these baselines, let's look at the demographic breakdowns.

Though the Conservatives won 40% of the vote overall, beating the NDP by nine points in 2011, the New Democrats might have taken more of the female vote than did the Tories, at 36% to 35%. The Liberals captured just 19%, with 4% of it going to the Greens.

The Liberals have made huge inroads among women, up 15 points. This came from both the NDP (12 points) and the Conservatives (7 points).

Interestingly, men and women's support is now rather uniform. The Liberals have 34% support among men, with 30% supporting the Conservatives and 23% the NDP. But in 2011, the Conservatives had an enormous advantage among male voters, with 45% support to just 26% for the NDP and 19% for the Liberals.

The Liberals have again picked up 15 points here, but most of that came from the Conservatives, who are down 15 points. The NDP has slipped three points.

Looking at the numbers this way gives us an indication of where support is coming from for the Liberals. They have improved their position equally among both men and women, but that female vote came from the NDP and the male vote came from the Conservatives. The effect has been to level the playing field, with each party garnering roughly half of their supporters from each gender. An interesting shift.

It should come as no surprise that the NDP won the youngest cohort of voters in 2011, with 38% support against 28% for the Conservatives and 20% for the Liberals. Today, however, the Liberals lead in this group with 34%, up 14 points. The NDP has dropped 11 points to 27% while the Conservatives have fallen seven points to 21%. The Greens are up four points to 10% among 18- to 29-year-old Canadians.

In 2011, 30- to 44-year-olds were somewhat representative of the population as a whole: 39% voted Conservative, 33% voted NDP, and 17% voted for the Liberals. They are still broadly representative, with 35% now supporting the Liberals, 27% the Conservatives, and 23% the NDP.

The Conservatives have suffered most among this group, dropping 12 points. The NDP has also fallen, by 10 points, while the Liberals have picked up 18 points - more than doubling their support among these voters.

This is a target group for all parties, considering the preponderance of family-friendly language used and family-focused policies proposed. It would appear that the Conservatives did a good job attracting these voters in 2011, but the Liberals are now managing it best.

The next group, who may be nearing retirement and have children heading to university, voted solidly Conservative in 2011: 41% to 30% for the NDP and 18% for the Liberals.

Now, this group is mostly split between the Liberals (33%) and the Conservatives (30%), with 22% supporting the NDP. The Liberals have picked up 15 points among these voters, with the Conservatives down 11 and the NDP down eight.

Finally, there is the oldest cohort of Canadians, an important demographic as they can be most counted upon to cast a ballot. They overwhelmingly supported the Conservatives in 2011, with 50% backing the party. The NDP took just 23% of the vote among this group, while the Liberals took 20%.

The NDP has held firm at 23%, but the Liberals have gained 15 points to move into a tie with the Conservatives, down 15 points, at 35%. If the Tories cannot win this voting block, they will not win the election.

When we break it down by age, we can see where the parties have suffered losses. The Conservatives have generally lost in uniform proportions, though perhaps took a bit more of a hit among older Canadians. The New Democrats have lost primarily younger voters, who have gone over to the Liberals, while older Canadians who backed the New Democrats in 2011 are mostly sticking with the party. The Liberals have generally gained in similar proportions across all demographic groups, but may have gotten their biggest uptick among Canadians who, coincidentally or not, are about the same age as Justin Trudeau.

All of this is relatively intuitive. The Conservatives are traditionally the party of older male voters, while the NDP would be expected to be the party of younger, primarily female Canadians. The Liberals enjoy uniform support levels among both genders and all age demographics, which seems to align with the broad appeal the party is seeking and is best placed to capture as the party in the centre. The Liberals remain in the best position one year before the next election. These numbers make it clear which demographic groups the NDP and Conservatives need to re-capture if they hope to win in 2015.