Tuesday, August 26, 2014

Two new polls give Liberals wide lead

Both Ipsos Reid and Abacus Data reported new national polling numbers yesterday, and both showed the Liberals leading the Conservatives by six or seven points. The results corroborate some of the other recent numbers we have seen. These suggest that the Liberals have rebounded, at the expense of the Conservatives, from what looked like a slump-in-the-making at the end of the spring.

The Ipsos Reid poll, conducted for Global News, was the first we have heard from the company at the federal level since April 17-22. Since then, the Liberals were up five points to 38% support, a jump that is outside the margin of error of a probabilistic sample of similar size.

The Conservatives were down two points to 31%, while the New Democrats were unchanged at 24%.

The Greens and Bloc Québécois had 3% apiece.

Abacus Data's last poll was conducted June 25-July 3. They have not recorded any major shifts since then, but the Liberals were up one point to 35%, followed by the Conservatives at 29% (down two points) and the NDP at 22% (up one point).

The Greens stood at 7% support, while the Bloc was at 5%.

Both pollsters recorded similar gender breakdowns. The Liberals were up by two points among men in the Abacus poll. The margin was four points according to Ipsos. Among women, both firms put the gap at 10 points between the Liberals and Conservatives.

I've highlighted above the three largest regions, but only in Quebec do the numbers look very close. There, both polls have the Liberals ahead of the NDP (echoing the results of the latest big-sample CROP poll) with the Bloc Québécois well behind.

The dissimilarities in British Columbia and Ontario are, on the face of it, important. In B.C., it is either a close Conservative-Liberal contest, or a Liberal lead with the NDP in second. In Ontario, it is either a wide Liberal lead or a virtual tie.

But if we take into account the margins of error (practically speaking, if not theoretically speaking since these are not probabilistic samples) we see that the disparities are really not so significant.

The chart below shows, simply calculated, where the two polls overlap for each of the parties. It gives a good indication of where things stand in each region.

Nationally, the Liberals are somewhere between 35% and 38%, while the Conservatives are clearly in second with between 28% and 32%. The NDP is in third with between 21% and 25%.

The Liberals are probably leading in British Columbia, where they are mostly ahead when taking into account the overlap. The NDP is probably in third, but overall the race is close.

The Liberals also probably lead in Ontario with between 35% to 41% against the Conservatives' 30% to 37%, and are most likely ahead in Quebec, with 31% to 41% against the 22% to 32% of the NDP. In Atlantic Canada, the Liberals are indisputably in front.

The Conservatives are comfortably in the lead in Alberta, but are well off their historical pace. They are also probably in the lead in the Prairies, but it is interesting that at the low end of the Tories' range and the high end of the range for the Liberals and NDP, the three parties are tied.
The Ipsos and Abacus polls would result in very different national scenarios in terms of seats. The Ipsos poll would give the Liberals 150 seats to 121 for the Conservatives and 67 for the NDP - enough to give the Liberals a comfortable minority government.

The Abacus poll is far closer, however, with 135 seats for the Liberals, 122 for the Conservatives, and 70 for the NDP.

If we combine the two results, taking the best and worst numbers in each of the regions, the Conservatives could conceivably come out ahead in the seat count with 140 to 133 for the Liberals. That would be on the margins of what is likely, just as a far larger Liberal victory of 152 seats to 103 for the Tories would be. But with these kinds of numbers, there is a great deal of scope for variation in the seat count. The Liberals need to be over the 40% mark to be in a good position to win a majority government.

The numbers above do give an indication of where the battlegrounds will be. For the Conservatives, much depends on their results in British Columbia and Ontario. For the NDP, it is Quebec and B.C. that are most important, while Ontario will probably make or break the election for the Liberals (I'd throw Quebec into that as well, but the Ipsos and Abacus polls were consistent there for the party).

Also of note is Alberta. With the Conservatives dropping significantly in the province to around 50%, it opens up the potential for a number of seats in Edmonton and Calgary to go to either the Liberals or NDP. It likely won't determine the fate of the government, but the eight-seat range for the Tories above could turn out to be very important. Admittedly, however, if the Conservatives are reduced to 21 seats in Alberta they are likely not doing very well in the rest of the country.

The only pollster that has been very active in 2014 that we have yet to hear from this summer is Angus Reid Global. As Angus Reid has had the race far closer than anyone else has, it will be interesting to see if they will change their tune or continue to set themselves apart from the pack.

Friday, August 22, 2014

Bloc falls in Quebec as Liberals move ahead

After a long drought of polls, two new ones were released yesterday. One, by Forum Research for the Toronto Star, I looked at for The Huffington Post Canada. The other, by CROP for La Presse, is the one we'll focus on here. And it is an interesting one.

The latest missive from CROP pegs Liberal support to stand at 38% in Quebec, up six points from CROP's last poll of June 12-16. That has moved them into first place, ahead of the New Democrats who were down three points to 32%.

The Bloc Québécois, in the midst of internal turmoil as Jean-François Fortin leaves the party and Claude Patry confirms he will not run for re-election in 2015, dropped five points to just 13%.

Though Nanos Research has had the Bloc below 13% on several occasions over the last few years, this is the lowest a Quebec-based polling firm has put the Bloc in recent memory. In all likelihood, this is the lowest the party has ever been since it was founded in 1990. What is the opposite of a honeymoon? Whatever it is, that is what new leader Mario Beaulieu is experiencing.

The poll asked Quebecers whether they felt the Bloc was still pertinent, and 65% of them said it wasn't. But worse is that 44% of sovereigntists agreed. Considering that Beaulieu has opted to focus on independence above all else, that is a crushing rebuke from the very people he is supposed to be firing up. More respondents said they would consider voting for the Bloc if it reverted to its traditional role of defending Quebec's interests.

The Bloc's drop of five points is outside the margin of error (or would be if this was a probabilistic sample) and is part of a recent trend of Bloc weakness. Of the eight polls conducted since Beaulieu won the leadership race, the party has been pegged under 20% in all but one of them. Prior to that, we have to go back 23 polls (to January) to find seven that has the party that low.

Perhaps most embarrassingly for the Bloc, which has run in the past on being able to 'block' the Conservatives, the party was just one point up on the Tories in Quebec. They were at 12%, up two points, while the Greens were at 5%, up one.

The Bloc's support among francophones dropped dramatically, down six points to just 17%. The Liberals were the beneficiaries, up 10 points to 34%. That helped them close the gap on the New Democrats, who were in front at 36%.

Among non-francophones, the Liberals led with 53%, followed by the NDP at 18% and the Conservatives at 16%. That was double their standing in June, however. The Greens were also up big, by nine points to 14%.

On the island of Montreal, the race was tied at 37% apiece for the Liberals and NDP, representing a 14-point gain for the latter. The Conservatives were third at 11%.

In the suburbs around the island, the race was also close: 33% for the Liberals vs. 32% for the NDP. The Bloc was third here with 16%.

The Liberals made a big jump in Quebec City, gaining 14 points to lead with 33%. The Conservatives dropped to 30%, while the NDP was down 15 points to 22% in the provincial capital.

And in the rest of the province, the Liberals were ahead with 44% to 32% for the NDP and 15% for the Bloc.

In terms of seats, the province-wide model gives the New Democrats 46, with 27 going to the Liberals and five to the Conservatives (the Bloc Québécois would be shutout). But, as I've discussed before, province-wide models in Quebec may not do the job well as the Liberals have gained support disproportionately outside of Montreal. Taking that into account, there are another eight seats that could fall to them instead of the NDP, narrowing the gap to 38 seats for the NDP and 35 for the Liberals.

On who would make the best prime minister, Justin Trudeau saw a four-point jump to lead with 31%, followed by Thomas Mulcair at 26%. That was a drop of five points. Stephen Harper was at 10%, while Beaulieu tied Elizabeth May at just 2%. By comparison, André Bellavance averaged 3.4% during his interim tenure, and Daniel Paillé averaged 4.3%. Back between 2007 and 2009, Gilles Duceppe averaged just under 20% in polls by Nanos.

The question that will only be answered in the coming weeks and months is whether this is a blip for the Bloc or the first sign that the party will not be able to hold on to any seats in 2015, which would be the final nail in the party's coffin. The Bloc was not en route to a triumphant return under Paillé, but he did have enough support to hold his seats and perhaps win a handful more due to vote splits. Under Beaulieu, it seems that the Bloc may not be able to hold onto the majority of its seats even before the election begins. One would expect the NDP, the party that benefited from the Bloc's downfall in 2011, to take advantage. But CROP, at this stage, gives the nod to the Liberals. Will that hold?

Wednesday, August 20, 2014

The polling plight of the little parties

The inclusion of parties in Canadian polling is quite standard. There are the Liberals, New Democrats, Conservatives (or whatever version of them exists at the provincial level), Greens, and the large Quebec parties. But what about the fringe parties in Canada?

One of the analysis topics that was requested during last year's Kickstarter campaign came from Greg Vezina, who asked me to look at the effects of polling (or not polling) the little parties. It was an interesting question, and that is the focus of this analysis.

For the purposes of defining a small party, I have included all parties that had between a 25% to 67% full slate of candidates, or a party that received less than 3% support with a fuller slate of candidates, or a party that was routinely included in polls with a slate of candidates less than 25% of the total.

I have ranked these small parties below by the average share of the vote they received in a riding in which they ran a candidate in a recent election. This was roughly estimated by multiplying the party's province-wide support by the number of seats divided by the number of candidates. 

I have also included below the average support registered in polls, when available, over the last five days of an election campaign. When there were no polls in the last five days, I used the last polls that were published.

There are a few cases that stand out, and I have highlighted these in yellow. These are small parties that were included in polls that had better performances than parties that were not included, despite having a smaller slate than the average of non-polled parties.

The Liberals in Saskatchewan and the Greens in Nova Scotia and Quebec may have benefited from being part of a national brand. But what was it about the Alberta Party, the Island Party, or the People's Alliance that gave them such a boost over parties who ran much larger slates, like the Ontario Libertarians in 2014 or the Ontario Freedom Party of 2011?

Granted, the People's Alliance in 2010 was included in the leaders' debates, and the Alberta Party got a lot of press in the run-up to the 2012 campaign thanks to a floor-crossing MLA. But nevertheless, their performance stands out from the pack.

Note also that the Evergreen party in Alberta's 2012 was included in some polls earlier on in the campaign, but not in the final stages, and is ranked here as the highest non-polled small party.

Now, the low performance of small parties and their non-inclusion in polls could simply be correlated rather than a case of causation. Perhaps these small parties were not included in polls because they were unlikely to do well or were getting scant media coverage. Or perhaps some of these small parties would have received more media coverage if they had been included in polls. But is it the responsibility of the media to give coverage to small parties that have little support, or the responsibility of pollsters to report how small that support really is, which in turn might raise the profile of those parties? It is a bit of a chicken or the egg question.

But there is certainly a difference. The average result for a party that was included in polls was 1.7% compared to 0.4% for parties that were not included. On a per-candidate basis, small parties included in the polls averaged 3.4% support, compared to 0.9% for parties that were not included. And this despite the average slate of small parties included in the polls being 54.7%, only slightly higher than the 44.9% of parties not included in the polls.

In other words, parties included in polls did 3.8 times better than parties that were not, despite running only 1.2 times the candidates.

It should be noted that when pollsters do try to gauge the support of smaller parties, they generally do quite well. And when they lump them all together in the 'Others' category, they do even better.

Electoral and polling results for 'Other' parties
So the pollsters may indeed be accurately recording the support for smaller parties already, and the effect would be minimal if they were included in all polls. 

But again, it might not be the case that being included in the polls was what boosted these parties, and rather their inclusion in the polls might have had everything to do with the support they were registering in the first place. But it is an interesting thing to consider. Should pollsters be including smaller parties in their polls if the party is running enough candidates?

In the grand scheme of things it may not matter or have a great influence on the outcome of an election. But already in two provincial elections in 2014, 347 people have run under the banner of these small parties and more than 150,000 people have voted for them. It is a question of greater importance to them.