Monday, February 28, 2011

Conservatives gain in monster Angus-Reid poll

On Saturday, Angus-Reid released the details of a huge poll of 6,482 members of their online panel. This gave them the ability to delve into and report the voting intentions of every province, including Saskatchewan and Manitoba and the four Atlantic provinces. It's all great fun, and in the end Angus-Reid shows that the Conservatives have made a gain since their last poll in early January.Compared to that poll, the Conservatives have gained five points and now lead with 39%. The Liberals are down two points to 26%, while the New Democrats are up one to 18%.

The Bloc Québécois is down two points to 9% nationally, while the Greens are down two points to 6%.

Angus-Reid reports that this poll has a margin of error of +/- 1.2%, 19 times out of 20. However, according to the MRIA it is inappropriate to report a margin of error for an online poll. Other pollsters who use an online panel, like Abacus Data and Léger Marketing, always report the margin of error of a random sample of the same size as their poll, rather than claiming that margin of error for their poll. Angus-Reid should probably do the same.

In any case, the only statistically significant variation at the national level, assuming a random sample, goes to the Conservatives and the Greens. The others are probably statistical wobbles.

The Conservatives are leading among both men and women, though the margin is far smaller among the fairer sex. Among men, the Conservatives have 44% support, compared to 24% for the Liberals and 15% for the NDP. Among women, the spread is 34%-28%-21%.

In Ontario, the Conservatives are up five points to 43%, as the Liberals drop six points to 30%. The New Democrats are up three points to 19%, while the Greens are down three to 7%.

The Bloc Québécois has dropped four points to 39% in Quebec, while the Liberals are down one to 21%. The Conservatives have gained seven points, and now stand at third with 20%. The NDP is down one to 14%.

In British Columbia, the Conservatives are down two points to 40%, followed by the NDP at 28% (+3) and the Liberals at 22% (+1). The Greens are down three points to 8%.

The Conservatives have dropped five points in Alberta, but still lead with 60%. The Liberals are up 10 points to 21%, while the NDP is down three to 9%.

I'll delve into the sub-regional numbers in a bit, but regionally the Liberals are leading in Atlantic Canada with 40%, down nine points. The Conservatives are up 16 points to 39%, while the NDP is up seven to 17%. Note that in Angus-Reid's last poll the "Others" were at 16%. They are now at 1%. This accounts for most of the shift.

And in the Prairies, the Conservatives are up 11 points to 55%, followed by the NDP at 22% (-14) and the Liberals at 19% (+4).

It would appear that the only variations of real statistical significance are the gains by the Conservatives in Quebec and by the Liberals in Alberta.

Now, to the sub-regional results. As we are very rarely treated with these numbers, I'll compare them to the 2008 election results.There has been very little change in Saskatchewan, as the Conservatives stand at 56% (+2 over the 2008 result), the New Democrats at 24% (-2), and the Liberals at 16% (+1). For some reason, Angus-Reid surveyed about 1,200 people in Saskatchewan, a huge amount.

In Manitoba, there has been a little change. The Conservatives are up five points to 54% and the Liberals are up two to 21%, while the NDP has dropped four to 20%. It puts the Winnipeg North by-election win in November in some context.

New Brunswick has seen even more change. Perhaps unsurprisingly considering the Progressive Conservative win in September in the province, the Conservatives are up six points to 45%. But the Liberals are up even more, gaining seven points to stand at 39%. Oddly, the NDP has fallen precipitously, from 22% to only 11% in the province.

Meanwhile, in Nova Scotia there has also been a shift, with the Liberals picking up 11 points to lead with 41%. The Conservatives are up six to 32%, while the NDP is down eight to 21%.

In Newfoundland & Labrador, the recent Telelink poll seems to be confirmed. The Conservatives are up a big 25 points to 42%, with the Liberals dropping 11 points to 36% and the NDP dropped 13 points to 21%.

And in Prince Edward Island, there has been very little change. The Liberals lead with 51% (+3), followed by the Conservatives at 40% (+4) and the NDP at 5% (-5).

With the results of this poll only, the projection model gives the Conservatives 19 seats in British Columbia, 27 in Alberta, 22 in the Prairies, 62 in Ontario, nine in Quebec, and 10 in Atlantic Canada for a total of 150. That's a gain of 19 seats from Angus-Reid's last poll.

The Liberals win six seats in British Columbia, one in Alberta, two in the Prairies, 29 in Ontario, 14 in Quebec, and 20 in Atlantic Canada for a total of 74. That's a drop of 23.

The Bloc wins 51 seats in Quebec, down four.

And the New Democrats win 11 seats in British Columbia, none in Alberta, four in the Prairies, 15 in Ontario, one in Quebec, and two in Atlantic Canada for a total of 33, up eight.

For regular readers, note that the riding-level projection model is in place for British Columbia, Alberta, and the Prairies. Ontario is close to being completed.

Also, I will be using this poll as a model to properly distribute support in Atlantic Canada. While the Conservatives are up in each province, the bulk of their gain comes in Newfoundland & Labrador. This will need to be taken into account in the projection model.

This poll serves to confirm what the others showed as the situation in mid-February: a double-digit Tory lead. But the Atlantic Canada numbers tell us something that other polls cannot: the Liberals still have very good numbers in the Maritimes, while the Conservatives will be the front-runners in Newfoundland. That changes the game quite a bit, and paints a very different picture of the situation in Atlantic Canada than the one we expected before.

From pre-writ polls to election day, history is not on Ignatieff’s side

Whenever a party is confronted with a yawning gap between themselves and their main rivals in a pre-election poll, it is usually waved off because “campaigns matter.” And they do. Campaigns give parties the opportunity to present a platform to Canadians and give voters a chance to get to know the leaders and their local candidates better. Campaigns also tend to shift pre-election polling results a great deal.

You can read the rest of the article on The Globe and Mail website.

Ontario and Quebec the keys to Tory gains

You can also read my column for The Hill Times here. A subscription is required, so why not subscribe?

It's a comparison of the four polls in early February (from Nanos, Ipsos-Reid, EKOS, and Harris-Decima) to the last time all four polling firms were in the field at the same time in early December.

I will be posting later today about Angus-Reid's new monster poll, so stay tuned!

Friday, February 25, 2011

Abacus has Conservatives still well in front

It appears that the pollsters now disagree once again. Abacus Data has come forward with a new set of numbers, showing that the Conservatives hold a massive 15-point lead, and arguing that the gap has not narrowed as EKOS Research has recently found.

However, we should not compare apples to oranges. EKOS conducted its poll over two full weeks, while Abacus's survey was conducted on one day. Without daily tracking of the EKOS poll, we cannot say with any real confidence that these two polls are contradictory. For all we know, in the last few days of EKOS's poll the Conservatives could have had a double-digit lead.

Consider also that a poll conducted on one day would be far more susceptible to individual events and how they have been portrayed in the media than a poll conducted over two weeks. Imagine a poll conducted today, with news that high-level Conservatives have been charged with breaking electoral law emblazoned on every front page.

In other words, this poll needs to stand alone and not be compared to the recent EKOS survey. If other polls show that the Conservative lead is still in place, then Abacus's poll will simply provide further evidence. If, on the other hand, they show that the Conservatives have lost support, there is a very good chance that Abacus was accurately recording the voting intentions of Canadians on February 23 only.

Enough with the preamble, now to the poll. We don't often get one-day polls, so it is an interestingly precise snapshot in time.Since Abacus's last poll in late January, the Conservatives have gained three points and now lead with 38%. The Liberals, on the other hand, have dropped four points and are down to a woeful 23%.

This poll was conducted online, and a random sample of similar size would have a margin of error of +/- 3.1 points, 19 times out of 20. But according to this paper, it is simplistic and inaccurate to say that, based on the 3.1 MOE, only the Liberal shift is statistically significant.

The fact of the matter is that properly calculating the margin of error for comparing two different sets of polls is not the same as just looking at the margin of error of a single poll. For the Conservatives, comparing their result in Abacus's last poll to their result in this poll would have a margin of error of +/- 5.2%, assuming that this would be a random sample. The Liberal margin of error over these two polls is +/- 4.3%. That means that neither shift is statistically significant.

The permutations of calculating a margin of error are complex. There are different margins of error for the different parties due to their level of support (parties with less support tend to have a smaller margin of error). For example, the margin of error for the New Democrats in this survey would be +/- 2.4%, rather than 3.1%. There are different margins of error for gauging the statistical significance of a gap between two parties (in this case, it is 4.7% for the Liberals and Conservatives), and as noted there are different margins of error when comparing one party's results in one poll to another.

Based on this paper it appears that virtually everyone talks about the margin of error incorrectly, including in the recent Canadian Press piece on polling. I'm not sure how to approach this in the future, but I will be taking more care before announcing any shift as statistically significant or not.

Today's post is quite tangential, so let's get back to it. The New Democrats are up one point to 19%, while the Bloc Québécois is up one to 11%. The Greens, meanwhile, are down one to 8%.

Regionally, we see a lot of the same things that other polls have shown. In Ontario, the Conservatives are up one point to 39%, while the Liberals are down seven to 29% (though apparently even that is not a statistically significant drop). The New Democrats are up two to 18%, while the Greens are up three to 12%.

In Quebec, the Bloc leads with 44% (+3), followed by the Liberals and Conservatives at 19% (+1 each). The New Democrats are down one to 15%.

In British Columbia, the Conservatives lead with 40% (-1), followed by the New Democrats at 30% (+1) and the Liberals at 21% (+3). The Greens are down four to 9%.

In Atlantic Canada, the Conservatives are leading with 39%, up nine points. The Liberals are down 15 to 29%, while the New Democrats are up four to 27%. Again, even these wild shifts appear to not be statistically significant.

The Conservatives are leading in Alberta with 70% (+15), while the Liberals are down 13 points to 11%. In the Prairies, the Tories have gained four points and stand at 48%, followed by the New Democrats at 26% (-1).

With this poll, I would project 19 Conservative seats in British Columbia, 28 in Alberta, 21 in the Prairies, 58 in Ontario, eight in Quebec, and 12 in Atlantic Canada for a total of 147, a gain of 14 seats compared to the projection for Abacus's last poll.

The Liberals would win six seats in British Columbia, none in Alberta, three in the Prairies, 31 in Ontario, 13 in Quebec, and 15 in Atlantic Canada for a total of 70, down 18.

The Bloc Québécois would win 53 seats in Quebec, down two.

The New Democrats would win 11 seats in British Columbia, none in Alberta, four in the Prairies, 17 in Ontario, one in Quebec, and five in Atlantic Canada for a total of 38 (+6).

For regular readers, note that the new projection model is in place for British Columbia and Alberta.

Abacus also helpfully asked the question Angus-Reid neglected to on the topic of Bev Oda. Do you know who she is? Amazingly, 46% of respondents said they did. It would appear that the 15% of Canadians who pay attention to politics are joined by another 31% who aren't exactly ignorant of what is going on in Ottawa.

Thursday, February 24, 2011

Tories drop in new EKOS poll, fall back to earth in Ontario

Once again, EKOS is out in front with a poll showing a new shift in voting intentions. When EKOS came out with a 12.5-point lead for the Conservatives two weeks ago, they were roundly criticized and their results questioned.

At the time, I argued that EKOS's results were not unreasonable, and a bevy of other pollsters came forward to confirm what EKOS was seeing. Now, as the polling firm pegs the lead at only 5.1 points, I can't help but wonder whether EKOS is going to be the first to identify a new shift again or whether the other pollsters will not confirm EKOS's findings this time in the coming weeks.Compared to that last poll, the Conservatives have dropped 4.9 points and now lead with only 32.4%. The Liberals, at 27.3%, have gained 2.5 points.

This IVR telephone poll has a margin of error of +/- 1.9%, 19 times out of 20. That puts these shifts outside normal statistical variation.

The other parties are wobbling within the margins, however. The New Democrats are up 0.6 points to 14.8%, the Greens are up 1.2 points to 11.9%, and the Bloc Québécois is up 0.6 points to 10.5%.

Note that, despite the large "Other" response (3%), that is no different than last time.

It can be posited that this drop could be the consequences of the Bev Oda affair, or it could be because the Conservatives tend to fall away from majority territory as soon as they come close to it. We can't really say, though Angus-Reid did find that 58% of Canadians believe Mrs. Oda should resign from cabinet. However, Angus-Reid neglected to first ask whether Canadians were aware of the controversy, spurring a few from the Ottawa press gallery to suggest that Canadians would demand the resignation of Len Blork, were they asked.

You can follow Len Blork, Minister of Grains and Oil Seeds (a plum portfolio if there ever was one!), on Twitter here. Despite the allegations, I'm projecting that the incumbency effect likely means he can hold on to his Nipawin seat.

Anyway, drilling down into the regionals we see that the main source of the Conservative drop has been in Ontario (MOE +/- 3.3%), where the party has handed over the lead back to the Liberals. They stand at 36.4%, up 6.1 points, while the Conservatives trail at 35.9%, down 5.6 points. The New Democrats are up 0.6 points to 14.2%. The Liberals are leading with 44.6% in Toronto, followed by the Tories at 31.9%. In Ottawa, the Conservatives are leading 39.6% to 38.5%.

In Quebec (MOE +/- 3.5%), the Bloc has gained 1.2 points and leads with 39.9%. The Liberals are up 2.6 points to 18.8%, while the Conservatives are down 3.9 points to 16.2%. It appears that this drop, outside of the MOE, is noteworthy. The New Democrats, meanwhile, are down 0.5 points to 11.4%. The Bloc leads in Montreal with 39.1%, followed by the Liberals at 22%.

The Conservatives are down 4.5 points to 32.9% in British Columbia (MOE +/- 7.1%), while the New Democrats are up 6.7 points to 25.2%. The Liberals have dropped 5.6 points to 20.9%, within striking distance of the Greens, who are up 5.9 points to 19.4%. All of these variations, however, are within the MOE. The Conservatives are leading in Vancouver with 39.3%, followed by the Liberals at 24.2%.

In Atlantic Canada (MOE +/- 7.5%), the Conservatives are leading with 36.8% (+4.7). The Liberals trail with 30.2% (-6.9), while the Greens are up 7.6 points to 16.8%. The New Democrats have dropped to fourth, down 4.6 points to 14.3%.

The Conservatives are down 12.3 points in Alberta (MOE +/- 7.5%) to 52.1%, trailed by the Liberals at 24.4% (+9.9). The Greens are up nine points to 17%, while the NDP is down 5.3 points to 5.7%. The Conservatives are leading in Calgary with 59%, followed by the Greens (!) at 20%.

Finally, in the Prairies (MOE +/- 8.3%) the Conservatives are down 2.5 points to 42.3%, but still hold a good lead over the NDP at 27.8% (+9.9) and the Liberals at 21.4% (-4.4).

With this poll, ThreeHundredEight would project 18 Conservative seats in British Columbia, 26 in Alberta, 20 in the Prairies, 46 in Ontario, six in Quebec, and 12 in Atlantic Canada for a total of 129. That is a drop of 22 seats from EKOS's last poll.

The Liberals would win six seats in British Columbia, two in Alberta, four in the Prairies, 49 in Ontario, 13 in Quebec, and 18 in Atlantic Canada for a total of 94, an increase of 11.

The Bloc Québécois would win 55 seats in Quebec, a gain of one over two weeks ago.

The New Democrats would win 11 seats in British Columbia, none in Alberta, four in the Prairies, 11 in Ontario, one in Quebec, and two in Atlantic Canada for a total of 29, a gain of nine seats.

The Greens would win one seat in British Columbia.

For regular readers, note that the new projection model is up and running for the British Columbian projections. All other regions are using the older model. I am open to individual, specific questions about these riding projections for British Columbia.

Will this poll dampen electoral speculation? Perhaps among the media, but at this point the party leaders probably have a good idea whether they are going to go into an election or not, and unless the polls become horribly bad (or terrifically good) for one of them I don't think they will be changing their minds. Political parties may not make their decisions based on public polls, but public perception is important, and opinion polls do play a role in shaping public perception of whether a particular political party is a "winner" or a "loser".

In the end, we will need to wait and see whether any other polling firms confirm this Conservative drop. There are some very high Green results in this poll, which probably need to be chalked up to the MOE. But since the overall shift in favour of the Greens is only to the tune of 1.2 points nationally, their results should not be considered a major factor in this shift.

Wednesday, February 23, 2011

The Incumbency Factor

Recently, I've been looking at the issue of incumbency and how to factor its effect into my upcoming riding-level projection model. The investigation resulted in an article for The Globe and Mail, but I had focused on one aspect of incumbency in that piece: the re-election rate.

I've continued my analysis and have now gone through all 308 ridings for the 2006 and 2008 elections. Rather than focus on re-election, I have focused on an incumbent's ability to out-perform, or under-perform, their party. This is very useful for projecting electoral outcomes.

For example, in British Columbia in 2006 the New Democrats increased their support as compared to the 2004 election by a factor of 7.5%. That isn't to say they increased their support by 7.5 points, but rather their support increased 1.075 times. However, in 2008, their support stood at only 91.3% of their 2006 total.

For NDP incumbents in British Columbia, then, I looked at whether they under-performed their party in 2006 (i.e., increased their support at a lower rate than their party did) and over-performed their party in 2008 (i.e., lost support at a lower rate than their party did). This would seem to be logical - incumbents should be less prone to losing support than, say, a random candidate in a riding in which the party stands no chance.

However, I didn't stop there. I broke it down by party and the number of times an incumbent had been re-elected before. Looking for patterns and trends, I found that in some cases there is a statistically significant incumbency effect.When an incumbent's party loses support in a province or region (region being the Prairies and Atlantic Canada), the incumbent loses support at a lower rate than their party in 75.1% of cases (333 such cases in 2006 and 2008). In only 24.9% of cases does an incumbent lose a greater proportion of support than the party as a whole. That's significant, and on average an incumbent out-performs a sinking party by 8%.

However, when a party gains support in a province or region, an incumbent performs worse in 53.8% of cases. Assuming that the incumbent vote has a higher degree of stability, we would assume that they would tend to increase their support at a lower rate than their party, but 53.8% of 195 cases is not very significant. It is even less so when you average out the "incumbency effect" when a party gains: 1.00. If you extend it to a few more decimal places you get a slightly negative effect, but the incumbency effect when a party is gaining seems to be virtually zero. If a party has a gain in support, incumbents tend to increase their support at the same rate in their riding.

Breaking down an incumbent's performance by party when that party gains support in a particular region did not show any significant variations. Liberal incumbents did much worse than their colleagues, but there was not a large enough sample size (14) to determine anything significant from it.

That was not the case when an incumbent's party loses support in a particular region. Breaking that down by party did show a large degree of variation, with New Democratic incumbents appearing to be the most secure. This would, on the face of it, make some sense. Voting for the NDP is very different from voting for the Liberals or the Conservatives - it is almost certainly a vote for an opposition party. This means that voters in NDP ridings tend to like their NDP MPs quite a bit, and/or believe strongly in the role of the NDP in Parliament. Voting Liberal or Conservative, on the other hand, seems to be a coin toss far more often.

After the NDP, Liberal incumbents performed best, followed by the Conservatives. There isn't a huge amount of variation between the three parties, but enough that it equates to roughly three points for a Conservative incumbent and five points for an NDP incumbent. The one party that showed a great degree of difference from the others was the Bloc Québécois. Their incumbents tend to see their vote shift at almost the same rate as their party as a whole.

There was very little variation, on the other hand, when breaking down incumbents (in cases where the party loses support) by the number of times they have been elected in the past. The factor varies only from 1.06 for 4th-time incumbents to 1.10 for 3rd-time incumbents, with 1st-time, 2nd-time, and 5th+-time incumbents falling in between.

But when a party gains support in a region, there does seem to be a difference between sophomore MPs and more veteran MPs. Sophomore incumbents (i.e., incumbents who were elected for the first time in the previous election) did better than their party (when their party increased its support in the region) in 60% of cases. This makes sense - when an MP is first elected voters are less sure of them. When they stand for election for a second time, there is a greater chance that more voters will flock to them, even at a greater rate than voters switch over to that party in a given province or region.

However, veteran incumbents (i.e., MPs who have been elected two or more times in the past in their riding) tend to do worse than their party as a whole, when their party is gaining in a region: 58.6% of veteran incumbents did worse than their party.

The last aspect of incumbency I looked at was when there was no incumbent. Whether by retirement, death, or disgraceful resignation, I looked at what happened in a riding after an incumbent MP did not stand for re-election. The result was that only in 13.4% of cases did the incumbent party do better in the open seat than their party did in the region or province as a whole. In 86.6% of cases, the rookie candidate for the incumbent party did worse than the party did in the province or region as a whole, and there was no significant variation between whether a party increased or decreased its support in the region. And the drop in support was significant, enough to reduce a healthy 40% to a risky 35%.

Incumbency is the last major factor I wanted to look at before building my new projection model. The results of this analysis have been added to the model with success, bumping the accuracy rating up by 10%.

I've completed the projection model for British Columbia, taking into account a variety of different factors. With the next projection update, the new model will be used for British Columbia, and other provinces will be added as they are completed.

I tested the model for both the 2006 and 2008 elections, and it performed at a high degree of accuracy. I will present the results of the tests later this week or next.

I am currently working on expanding the new projection model into the other provinces. I'm working on Alberta at the moment, and hope to have it all up and running in the next few weeks. Every factor input into the model is verifiable, testable, and evidence-based. The tests of the model have, so far, proven its validity. When the test results are presented, I will provide detailed methodology as well. The new projection model will provide projections for all 308 ridings, taking into account their individual characteristics where possible.

I'll leave you with one little tidbit on what the projections for British Columbia are now showing: it's beneficial to the NDP. But the new model still shows that the Liberals are poised for gains in the province.

Tuesday, February 22, 2011

PCs lead in Alberta and Ontario, PQ in Quebec

My list of topics to cover grows each day, so instead of taking these provincial polls one at a time here are the latest numbers from Ontario, Alberta, and Quebec, with a provincial polling trends update.

We'll start with a Nanos poll from Ontario, conducted at the end of January and the beginning of February. It shows that the Progressive Conservatives hold a narrow lead over the governing Liberals.Nanos's last poll for Ontario dates from February 2010, so this gives us an opportunity to determine how things have played out over the last 12 months.

Not much has changed. The Progressive Conservatives now hold the lead, and have gained five points. They stand at 43%, followed by the Liberals at 39%, down two points. The New Democrats are unchanged at 13%, while the Greens have dropped three points to 5%.

This telephone survey has a margin of error of +/- 4.4%, 19 times out of 20. Considering the narrow shifts, only the Progressive Conservative gain seems to be statistically significant. But Ipsos-Reid's last poll in January showed a similar gap between the two main parties.

With this poll, ThreeHundredEight would project 62 seats for the Progressive Conservatives, 41 for the Liberals, and four for the New Democrats. That means a majority government for Tim Hudak.

That is, apparently, not a huge problem for Ontarians. Asked whether the leaders would have a positive or negative impact on their local voting intentions, respondents said that Hudak had a more positive impact (36.9%) than a negative one (12.7%). This contrasts with Dalton McGuinty's 26.8% positive to 33.3% negative score.

Andrea Horwath of the NDP has a positive net effect, with 24.1% saying she had a positive impact and 11.4% saying she had a negative impact.

As to who would make the best premier, Tim Hudak tops the chart with 32.3%, followed by McGuinty at 23.4% and Horwath at 9.2%. "None of the above" is in the race as well, at 11.5%.

The race is also surprisingly close in Alberta, at least compared to the province's homogeneous political history. An Environics poll conducted at the end of January, in the midst of Premier Ed Stelmach's resignation announcement, shows that the Progressive Conservatives still hold the advantage in the province, but are being closely trailed by the right-wing Wildrose Alliance.Environic's last poll conducted in November showed a narrower gap between the two parties. The Progressive Conservatives have gained four points since then, and now lead with 38%. The Wildrose Alliance has dropped six points to 26%, while the Liberals are up three points to 22%.

The New Democrats are down three points to 10%, while the Others are at 4%. How much of that vote is occupied by the centrist Alberta Party is, unfortunately, unknown.

This telephone survey has a margin of error of +/- 3.1%, 19 times out of 20.

The Progressive Conservatives are leading in every part of the province, with 36% (+4 from November) in Edmonton, 34% (-2) in Calgary, and 43% (+10) in the rest of Alberta.

In Edmonton, the race is between the PCs and the Liberals, who are at 27%. The Wildrose Alliance has dropped seven points in the capital, and are third with 18%.

In Calgary, however, the Wildrose Alliance is not far behind the PCs with 31%, while the Liberals stand at 24%.

And in the rest of Alberta, the Wildrose Alliance trails the PCs with 29%, with the Liberals in third at 15%.

With this poll, I would project 57 seats for the Progressive Conservatives, 14 for the Wildrose Alliance, 12 for the Liberals, and four for the New Democrats. The Progressive Conservatives would win 13 seats in Calgary and 16 in Edmonton, while the Wildrose Alliance would win nine in Calgary and none in the provincial capital.

The Liberals would win six of their seats in Calgary and five in Edmonton, while the NDP would win all four of their seats in Edmonton.

Next, we will take a look at Quebec, where Léger Marketing has been furiously polling. The firm has been conducting two sets of polls, one for Le Devoir and the Montreal Gazette, and the other for the QMI Agency. As the latter set of polls are focused on the emergence of a political movement led by François Legault, and is less detailed, it makes more sense to compare this latest Léger poll to the last poll they conducted for Quebecor.Since then, the Parti Québécois has lost three points but still leads with 34%. In fact, the gap has widened as the Liberals have dropped four points to 29%.

The ADQ is steady at 15% while Québec Solidaire has gained three points. They now stand at 11% in Quebec.

A random sample of 1,006 people would have a margin of error of +/- 3.1%, 19 times out of 20. This makes the shifts in this poll relatively benign.

The PQ leads among francophones with 41%, followed by the Liberals at 20% and the ADQ at 14%. Among non-francophones, the Liberals dominate with 64%. The ADQ is next with 13% while the Greens stand at 10% among this demographic.

With this poll, ThreeHundredEight would project 69 seats for the Parti Québécois, 41 for the Liberals, 13 for the ADQ, and two for Québec Solidaire. More or less par for the course.

But it is on the question of Legault's new movement that this poll is interesting. Contrary to the last time Léger polled, Legault's movement has not been called "centre-droite" in their questioning. This is good, because Legault has refused to pigeon-hole himself but has called his movement "gauche-efficace", or an effective left.

Fully 30% of Quebecers are prepared to vote for his phantom party. The PQ would be reduced to 24%, tied with the Liberals, while the ADQ would drop to only 9%. No wonder that Gérard Deltell is openly talking about an alliance with Legault.

Though the projection model is not designed for the inclusion of a completely new party, a crude projection would give Legault 63 seats, a majority of one. The PQ would win 34 seats and the Liberals 25, while Québec Solidaire would win three seats.

Of course, Legault would have to find 62 people to sit with him. Who would these people be? How would Legault run a campaign with a bunch of political novices? Who knows.

Nevertheless, Quebecers seem open to Legault, with 47% saying he should launch a party. Another 28% said he shouldn't, and 25% said they didn't know.

What's interesting is that when asked whether they agreed with his positions, almost half (46%) said they didn't know, while 39% said that they did agree with him. Apparently, Quebecers just want another option, whatever it is. Without crosstabs we don't know, however, whether that 46% of people who don't know Legault's position were drawn from the 53% of people who said that Legault shouldn't launch his party or who had no opinion.

In any case, it is pretty clear that Quebecers are open to something different. Once that "something different" becomes "something real", however, I suspect voting intentions will shift once again.

Now to the provincial polling trend update. This chart shows the averages of all of the provincial polling results released each month, with polls that had field dates that straddled two months being part of the average for both those months. Months without any polls are considered to have the same levels of support for each party as the last month in which there was a poll. This gives us some straight lines that only shift once new polls appear.In all cases, the red corresponds to the provincial Liberal party. In most cases, the blue corresponds to the various Conservative or Progressive Conservative parties in each province, the orange corresponds to the New Democratic parties, and the green corresponds to the various Green parties. The exceptions are:

Green = Wildrose Alliance (Alberta)
Dark Green = Saskatchewan Party (Saskatchewan)
Light Green = Greens (Saskatchewan)
Dark Blue = Parti Québécois (Quebec)
Light Blue = Action Démocratique du Québec (Quebec)
Orange = Québec Solidaire (Quebec)

Monday, February 21, 2011

Big shift on the Prairies changes little in Nanos poll

The latest poll from Nanos Research helps confirm some of the trends that other polls have indicated, but in the end the 13.1-point lead is smaller than it looks.The Conservatives have gained 1.8 points over Nanos's last poll in late November/early December, and lead with 39.7%. The Liberals have dropped 4.6 points and trail at 26.6%, while the New Democrats are up 1.7 points to 18.9%.

This poll was taken before the Bev Oda affair. Its effect on national voting intentions, if there will be any, has yet to be recorded.

The Bloc Québécois is down 0.3 points to 9.9%, while the Greens are up 1.7 points to 4.9%.

The margin of error in this telephone survey is +/- 3.1 points, 19 times out of 20, and 18.8% of respondents were undecided. Note that, unlike other pollsters, Nanos does not prompt survey takers with party names. This tends to reduce Green support compared to prompted polls, but according to one pollster I've spoken to who used both methods in 2008, prompted results tend to be more accurate.

But when we look at the regional breakdown, we see that much of the Conservative gain and Liberal loss is due to huge variations in the Prairies, while the New Democrats make their gain on the backs of Quebecers and Ontarians.

We'll start with the Prairies (MOE +/- 7.8), which for Nanos includes Alberta. There, the Conservatives have gained 18.9 points and now lead with 64.6%. That's a huge jump, representing roughly 3.2 points at the national level - less than the Conservatives actually gained. The Liberals, meanwhile, are down 15.6 points to 18%, a drop equating to roughly 2.7 points nationally. Both of these shifts are outside of the margin of error so we are probably looking at something real, but it means very little in the big scheme of things.

Why? Because despite strength in the Prairies, the Conservatives are showing weakness in British Columbia, Ontario, and Atlantic Canada - at least compared to Nanos' last poll from more than two months ago.

And that's something that should be noted - the last round of polls from Harris-Decima, EKOS, and Ipsos-Reid were being compared to their previous polls in January. Nanos Research, on the other hand, has not reported for some time.

In Ontario (MOE +/- 6.5), the Conservatives are down 3.3 points to 39%, while the Liberals are down 2.6 points to 32.8%. The NDP is the one making gains, with a 4.1 jump to 23.4%. The Greens are up 1.8 points to 4.8%.

The Bloc has dropped 2.8 points in Quebec (MOE +/- 6.7) to 37.3%, but are still well ahead of the Liberals (24.4%, down 2.3) and the Conservatives (20.2%, up 1.9). The New Democrats have gained 4.1 points and are at 16.8%, which appears to be the first telephone poll result to put the NDP at over 16% in Quebec.

In British Columbia (MOE +/- 9.2), the Conservatives are down 4.8 points to 44.6%. The Liberals are up 1.2 points to 26.2% while the NDP is down one point to 21.3%. The Greens are up 4.6 points to 7.9%.

Finally, in Atlantic Canada (MOE +/- 10.6) the Conservatives are down 6.4 points to 37.1%, while the Liberals are down four points to 32%. Most recent polls are putting the Tories in front on the East Coast, which is definitely a shift. The New Democrats are up 2.9 points to 20.4%, while the Greens are up 7.4 points to 10.4%.

With the results of this poll, ThreeHundredEight would project 24 Conservative seats in British Columbia, 49 in the Prairies (I'm currently not equipped to project for polls which combine Alberta, Saskatchewan, and Manitoba, so have given the Conservatives all seats in Alberta and the seats currently projected to go their way in the Prairies), 52 in Ontario, nine in Quebec, and 12 in Atlantic Canada for a total of 147. That's a drop of one seat from Nanos' last poll.

Yes, that's right. In this poll, the Tories have run up the numbers in the Prairies, where they have little to gain. Even if we give them all 56 seats in the region, they would still only be at 154 in total. Their Ontario numbers just aren't strong enough.

The Liberals would win nine seats in British Columbia, five in the Prairies, 36 in Ontario, 15 in Quebec, and 17 in Atlantic Canada for a total of 84, down five.

The Bloc would win 49 seats in Quebec, down two.

The New Democrats would win three seats in British Columbia, two in the Prairies, 18 in Ontario, two in Quebec, and three in Atlantic Canada for a total of 28, a gain of eight compared to Nanos's last poll. Despite a good national result, their numbers are too weak on the east and west coasts.

Nanos also looked at who would make the best Prime Minister. Stephen Harper topped the chart with 34.5%, up 6.1 points from last time. Jack Layton was next with 14.3%, down 2.1, while Michael Ignatieff scored only 13.6% (-1.9). That was less than the "none of the above" option, which stands at 13.9%.

Gilles Duceppe was at 22.8% in Quebec while Elizabeth May earned 4.5% of responses.

This Nanos poll will serve to help confirm the strong lead that the other pollsters have shown, but it isn't a necessarily good poll for the Tories. As others have indicated, the Conservatives are starting to rub up against their ceiling, making gains in regions where they have little seat gains to make. It really highlights how Quebec is hurting them - if they were able to bump their numbers up to 25% or more they could start to seriously hope for a majority. Instead, they are planning on incremental, seat-by-seat gains in Ontario. It's a strategy that could work, but leaves little margin for error.

AM radio or YouTube? How parties reach their supporters

Marketing is almost always targeted at a particular audience. That’s why you don’t see sugary breakfast cereal commercials during a cop drama or life insurance ads during episodes of Glee. Political marketing is no different, and recently the Conservatives purchased advertising time during the Super Bowl and on French-language television during Montreal Canadiens games. The choice was no coincidence.

The rest of the article can be read on The Globe and Mail website.

Nanos has a new poll out this morning. Hey, guess what? It says a lot of the same things the other polls have said. I'll write about it later today.

But if you didn't check the blog this weekend, take a look at my post on decimals yesterday.

Sunday, February 20, 2011

Use of decimals in polls: a thought exercise

Yesterday on CBC Radio's The House, Allan Gregg of Harris-Decima spoke more about what he has said recently on the At Issue Panel and in last weekend's Canadian Press piece by Joan Bryden on polling. Among other things, he spoke about reporting polls to the first decimal point.

He called pollsters who report in this way (EKOS and Nanos being the only ones who do so) "tremendously naive, or ridiculously deceitful". Things are getting personal. But competitors criticizing each other? Stop the presses!

But does he have a "point"? (snicker)

As Frank Graves of EKOS has mentioned to me, why conduct polls with larger sample sizes if you don't take advantage of their greater precision? Harris-Decima's last poll had a sample of over 3,000 people, but they rounded off their poll results. Yet, Harris-Decima's poll mentioned a margin of error of +/- 1.8 points. That becomes a rather useless number when you round off polling results.

Let's conduct a thought exercise using Harris-Decima's most recent poll, focusing on the Conservative result.Harris-Decima reported the Conservatives being at 37% support. With rounding, however, that could put the Conservatives at anywhere from 36.5% to 37.4%, and with the 1.8 point margin of error that means the Conservatives could be between 34.7% and 39.2%. In effect, it increases the margin of error to 2.3 points, rather than 1.8 points.

So, rounding off poll results gives us a far less precise and even more cloudy picture of the situation. The standard poll has a margin of error of 3.1 points, which gives a rounded off result of 37% a range of between 33.4% and 40.5% (or 33% to 41%, if we're rounding). If that result was reported as 37.0% instead, the range would be 33.9% to 40.1% (or 34% to 40%, with rounding). And that is with the exact same poll result.

Sure, an argument can be made that reporting to the first decimal point might be providing more precision than is necessary. But if polling results are going to be rounded off, perhaps reported margins of error should be as well. It certainly sounds better to say that a poll is accurate within 1.8 points rather than two points, but it would appear to be providing the same "unnecessary" precision.

To paraphrase Nate Silver, more precision is better than less. It is up to us to use that extra precision correctly, and within context.

Friday, February 18, 2011

Conservatives make big gain in new projection

With all of the hubbub surrounding the latest polling results, a projection update seems timely. As I have an article for The Globe and Mail appearing on Monday about political marketing, a projection update couldn't wait any longer. And the shift is significant.Compared to my last projection of February 7, the Conservatives have gained 1.1 points nationally, giving them six more seats. That now puts them at 144 in total, a gain of one seat over their current standing in the House of Commons, not counting the seats recently vacated by Jim Prentice and Jay Hill.

The Liberals, on the other hand, are sinking. They've dropped a full point and are down four seats to 92. That still represents a gain of 15 seats compared to now.

The New Democrats are down 0.4 points to 15.1%, and have dropped one seat in the projection to 20. That's a loss of 16 seats.

The Bloc Québécois is up 0.1 points to 10.0%, while the Greens are up 0.2 points to 8.5%. This projection is, of course, an indication of what Canadians could expect if an election were held today.

Regionally, the Conservatives have gained everywhere except in British Columbia. We'll start there.

The Conservatives are down one point to 38.4% in the province, and are trailed by the Liberals. They're up 1.3 points to 26%. The New Democrats, meanwhile, are down 0.5 points to 21.2% and the Greens are up 0.1 points to 12.1%. The Conservatives would win 22 seats (-1 from February 7th), the Liberals 10 (+1), and the NDP four (unchanged).

In Alberta, the Conservatives have gained 0.8 points and are projected to be at 60.8% support. The Liberals are down 0.8 points to 18.9%, while the NDP is up one point to 10.7%. The Greens are down 0.4 points to 7.8%. The Conservatives would win 27 seats and the Liberals one, unchanged from the last projection.

The Conservatives have gained 0.5 points in Saskatchewan and Manitoba, and lead with 46.6%. The Liberals are down 0.2 points to 24% in the Prairies, while the NDP is down 0.5 points to 20.2%. The Greens, at 7.5%, have gained 0.3 points. The Conservatives would win 21 seats, the Liberals five, and the New Democrats two, unchanged from last time.

Ontario is showing some real movement, with the Conservatives gaining 2.1 points and getting over the 40% mark. They now lead with 40.4%, while the Liberals have dropped 1.5 points to 35.2%. The New Democrats are down 0.9 points to only 14.2%, while the Greens are up 0.2 points to 9%. The Conservatives are projected to win 54 seats (+4), the Liberals 42 (-3), and the New Democrats 10 (-1).

In Quebec, the Bloc has dropped 0.3 points but still leads with 39.7%. The Liberals have slipped one point to 20.4%, while the Conservatives are up a point to 19%. The New Democrats have gained 0.6 points and stand at 13.7%, and the Greens are down 0.2 points to 6.3%. The Bloc is projected to win 52 seats (-1), while the Liberals would win 14 (unchanged), the Conservatives would win eight (+1), and the New Democrats would win one (unchanged).

Finally, in Atlantic Canada the lead has swapped. The Conservatives are now in front with 36.2% (+2.3), representing their largest gain in the country. It follows that the Liberals would have their largest loss in the country, as they have dropped 3.4 points to 35.8%. It wasn't so long ago that the Liberals were well over 40%. The New Democrats are showing a little life, and have gained 0.7 points. They are now at 19.5%, ahead of the Greens who are up 0.8 points to 6.3%. The Conservatives are projected to win 11 seats in the region, up two, while the Liberals would win 18 (-2) and the New Democrats three.

The one lifeline for the Liberals in all of this is the weakness of the New Democrats. My projection for them is relatively low, but it is difficult to see the New Democrats making significant gains or keeping the seats they currently hold when they have dropped five points in British Columbia, five points in the Prairies, four points in Ontario, and six points in Atlantic Canada. At 15.1% nationally, the New Democrats would be at their lowest level of support since the 2000 election.

But if the Conservatives are able to maintain this level of support, they will enter the next election campaign from a very strong position. They can stand to lose some support and still form government, and would be well within reach of a slim majority. Will this make the Conservatives more bullish, pushing them to engineer the downfall of their government? I think not - while a majority is a possibility, it is not anywhere near a certainty or even a likelihood. Far safer to continue governing as if they have a majority, which they have done for several years.

On Twitter? Follow me @308dotcom!

Thursday, February 17, 2011

Provincial and federal Tories lead in Newfoundland & Labrador

No, I will not make a joke about screech in this blog post. But what I will do is take a look at two new polls released by NTV for Newfoundland & Labrador, as well as a by-election which took place Tuesday.

It's not often that we are blessed with a federal poll conducted for just one of the Atlantic provinces. And with the power of the ABC campaign transforming the political landscape in 2008, Newfoundland & Labrador stands to be one of the more interesting provinces to watch if a federal election takes place this year. Will the Conservatives continue to be shut out from the island, or will they make a comeback?

The new poll conducted by Telelink for NTV indicates that the federal Conservatives are back in full force in Newfoundland & Labrador. Or does it?We have no previous Telelink poll to compare these results to, so we shall compare them to the 2008 federal election.

In the NTV report, the intentions of decided voters and decided/leaning voters were reported without a distribution of the undecideds, contrary to common practice. But after removing the non-leaning undecideds from the equation (they number 27.9%, relatively high but not extraordinarily high) we get 51% for the Conservatives, 34% for the Liberals, 13% for the New Democrats, and 3% for the Greens/Others.

That represents a gain of 34 points for the Tories and losses of 13 and 22 points for the Liberals and New Democrats. Seems like a sea change indeed.

That the Conservatives are in the race again is shown by the fact that 32.1% of Newfoundland & Labradorians are decided Tory supporters.

But hold the phone - Telelink? As far as I can tell, they are not a proper public opinion research firm. They are a call centre, with public opinion surveys being one of things they do. You can also outsource your customer service to them.

That isn't to say that their results aren't reliable. Apparently, in the 2007 election they were more accurate than the Corporate Research Associates, the one active polling firm in Atlantic Canada.

However, there is a bit of a problem with this poll. I made some inquiries, and apparently the provincial voting intentions question was asked before the federal voting intentions question. That is a bit of a problem, particularly in a province like Newfoundland & Labrador which has a very different provincial political scene. As the vast majority of decided respondents said they were going to vote Progressive Conservative at the provincial level, if the very next question is how they intend to vote at the federal level there is a much higher probability that they would also respond Conservative. So take these results with a large grain of sea salt.

But leaving that aside, if accurate this poll changes things in Newfoundland & Labrador. Traditionally, with the exception of a close race in 2006, the province has always voted Liberal. The party hasn't been below 40% since 1984 when Brian Mulroney's Progressive Conservatives swept the country.

With these polling results and using a proportional swing method of seat projection, the Conservatives would win four seats and the Liberals three. However, I'm currently looking in-depth at the issue of incumbency, and based on my preliminary findings I would project that the Liberals would retain St. John's South - Mount Pearl and the New Democrats would keep St. John's East. That pushes the Conservative seat projection to two: Avalon and Random - Burin - St. George's, while the Liberals would also win Bonavista - Gander - Grand Falls - Windsor, Humber - St. Barbe - Baie Verte, and Labrador.

Provincially, there has been very little change in voting intentions since the 2007 election.The Progressive Conservatives lead with 70% (unchanged), the Liberals follow with 23% (+1), and the New Democrats bring up the rear with 6% (-2).

If we compare that to the Corporate Research Associates' November poll, that is a five point loss for the Tories, a two point loss for the NDP, and a seven point gain for the Liberals.

With this result I would project 43 seats for the Progressive Conservatives, four seats for the Liberals, and one for the New Democrats. It's virtually the same result as in 2007, but with one seat gain by the Liberals.

The new premier, Kathy Dunderdale, is the favourite leader at 65.1%, or 79% of decided respondents. Yvonne Jones is next with 11.5% (14%), while Lorraine Michael of the NDP is at 4.2% (5%). Mrs. Dunderdale has, so far, managed to keep up with the dominant numbers Danny Williams had enjoyed before his resignation.

Speaking of which, on Tuesday there was a provincial by-election in Humber West (part of Corner Brook) to replace the former premier. The result came as no surprise, but indicates that the Liberals should be competitive in this fall's general election.Progressive Conservative Vaughn Granter won the by-election with 63.6% of the vote. Mark Watton of the Liberals placed second with 33.1%, while Rosie Myers of the NDP finished with 3.4%.

That represents a significant drop in support from the 2007 election when Danny Williams received 87.9% of the vote (there was no NDP candidate). But it is almost the same result as in the 2003 election, when Mr. Williams was leading his first general election campaign.

There's not too much to read into this by-election result, except that the departure of Danny Williams has, perhaps, opened a door for the Liberals to make some small gains. He also seems to have given the federal Conservatives a new lease on life. An attention-grabber while in power, even gone the former premier still makes his province one to watch.

Wednesday, February 16, 2011

Little change in Harris-Decima poll, and a comparison of recent results

Yesterday, Harris-Decima added their voice to the polling cacophony, showing very little change in their national numbers but giving further evidence of the Conservatives' double-digit lead over the Liberals.

After this report on the Harris-Decima poll, I take a look at their numbers in conjunction with those of EKOS and Ipsos-Reid. Three polls with the same inaccuracies? It seems unlikely.

In this poll, as in others, statistically significant shifts in voting intentions in Ontario are the story.First off, compared to Harris-Decima's last poll the Conservatives have a gained only a point, and now lead with 37%. The Liberals are down one to 27%, while the New Democrats are also down one point to 14%.

The Bloc Québécois and Greens have each gained a point and stand at 10%. All of these shifts are within this telephone poll's +/- 1.8% margin of error (19 times out of 20).

As Harris-Decima has reported their regional margins of error, I will not round them as I did for Ipsos-Reid's poll yesterday. I will use them, however, to reverse-engineer and estimate the poll's sample sizes for my model.

In Ontario (MOE +/- 3.1), the Conservatives have gained four points and now lead with 43%. The Liberals are unchanged at 34%, while the New Democrats are down three to 12%. The Greens are unchanged at 10%. As in other recent polls, the Conservatives have made gains in the province over-and-above any likely statistical wobbling.

The Bloc Québécois is steady at 40% in Quebec (MOE +/- 3.6), while the Conservatives (+1) and Liberals (-1) are tied at 19%. The NDP is down two to 12% in the province. More good results for the Tories.

In British Columbia (MOE +/- 5.0), the Conservatives are up one point to 35%. The Liberals, down three, trail with 29% while the NDP is down five to 19%. The Greens have gained seven points, and are in it at 16%.

The Conservatives have gained four points in Atlantic Canada (MOE +/- 5.6) and now lead with 39%, echoing Ipsos-Reid's results. The Liberals are down 13 points to 29%, while the NDP is up nine to 24%.

In Alberta (MOE +/- 5.6), the Conservatives have dropped five points to 56%, while the Liberals are up three to 21%. The only noteworthy shift here is a six point gain for the NDP, who stand at 12%.

And in the Prairies (MOE +/- 5.6), the Conservatives have dropped only one point and lead with 48%. The Liberals are up three to 22%, while the NDP is steady at 20%.

With this poll, the Conservatives would win 20 seats in British Columbia, 27 in Alberta, 21 in the Prairies, 61 in Ontario, eight in Quebec, and 12 in Atlantic Canada for a total of 150. That's 12 more than in my last projection for a Harris-Decima poll.

The Liberals would win 12 seats in British Columbia, one in Alberta, four in the Prairies, 37 in Ontario, 13 in Quebec, and 16 in Atlantic Canada for a total of 85, down nine.

The Bloc Québécois would win 53 seats in Quebec, unchanged.

And the New Democrats would win four seats in British Columbia, none in Alberta, three in the Prairies, eight in Ontario, one in Quebec, and four in Atlantic Canada for a total of 20, down three.

Harris-Decima also looked into leadership, finding that 46% of Canadians have a favourable impression of Stephen Harper. Another 43% have an unfavourable impression, and according to the press release this is the first time Harper has had a net positive rating since November 2009.

Michael Ignatieff, on the other hand, is at his lowest level ever at 25% favourable and 51% unfavourable.

Jack Layton splits 44% to 38%, Elizabeth May splits 25% to 30%, and Gilles Duceppe splits 53% to 30% (in Quebec only).

A comparison of recent polls

When EKOS showed a 12.5-point lead for the Tories on Friday, the Conservatives objected and the poll was called an outlier. Then Ipsos-Reid came along and confirmed EKOS's numbers on Monday, and Harris-Decima did the same on Tuesday.

But what of their methodological limitations? The inability to get a truly random sample? The regional sub-samples being too small to tell us anything? Why, these polls are unreliable and we should just stop talking about them!

Well, no. Polls aren't perfect, and some are less perfect than others, and there are some methodological hurdles to overcome in the future. But polls still work, and are a reasonable measure of public opinion. The proof is in the pudding, as they say, and all three of the polling firms that have reported over the last week (and who were in the field on overlapping days) have told the same story of a shift in public opinion.

Not even the small regional sub-samples varied widely. Ipsos-Reid, EKOS, and Harris-Decima all conduct their surveys by telephone, but not in the same way. Ipsos-Reid and Harris-Decima appear to use traditional telephone methods, while EKOS uses an IVR system which reaches both landlines and cell phones. And sample sizes were very different: EKOS's poll surveyed 1,652 people, Ipsos-Reid's surveyed 1,001 people, and Harris-Decima surveyed 3,025 people. For a small region like Atlantic Canada, the MOE varied between 14% in the Ipsos-Reid poll to only 5.6% in Harris-Decima's poll. And yet...We see very little difference in their results for the Conservatives and the Liberals. What's more, there is even little difference in how the vote has shifted in each of their polls.

In British Columbia, the Conservatives in each poll have gained compared to the last polls conducted by these firms, previous polls which were all conducted at about the same time in January. The Liberals lost support in all three polls as well.

In Ontario, the Conservatives gained between 4 and 6 points in all three polls, while the Liberals either held steady, lost four points, or lost eight points. That tells a significant story of Tory gain and Liberal loss, and in Quebec the Conservatives have gained in every poll.

At the national level, the results were 37%, 39%, and 37% for the Conservatives and 25%, 25%, and 27% for the Liberals.

Clearly, these guys must know what they're doing. Or they are all wrong in the exact same way.

But does it matter? An election could be two or three months away, or more than a year away. What do these polls say about how Canadians will vote at the point? Well, not much - but that isn't what these polls are arguing. And that doesn't make them completely useless.

Oddly enough, a similar discussion is taking place in the United States. Nate Silver of FiveThirtyEight recently wrote on his blog about some presidential primary polls. He was criticized for it, as these curmudgeons argued that the polls were meaningless. I'll quote what Nate had to say on the issue today. The parallels between the American pre-primary season and this Canadian pre-writ period are obvious. The full post can be found here.

However, it is clearly incorrect to suggest that a candidates’ post-primary favorability numbers cannot be predicted at all by what they are early on. For the 18 candidates in the study who actually endured a primary (not counting George W. Bush in 2004, who did not), the correlation of the candidate’s net favorability ratings between the two periods was .63.

That is not a terribly strong correlation by any means, and the number might change some if the study covered more years and included candidates like Mr. Dole and Mr. Reagan. Nevertheless, the relationship is highly statistically significant. Even at this early stage, polls tell us something — not everything, not a lot, but something — about how the candidates are liable to be perceived next year following the primaries.

...

Mr. Nyhan
[one of Nate's critics] has written that early primary polls “don’t matter” and that they are “useless” — and several other bloggers have echoed these statements. That just isn’t true. Yes, as a first approximation, the rule of thumb “don’t pay much attention to early primary polls” is probably better than “pay a lot of attention to early primary polls,” given the way that the media tends to overrate their importance. But Mr. Nyhan’s statement is hyperbolic.

There are many aspects of politics that can be investigated, reported on, and studied. Polling is one of them. Clearly, not everyone believes polls are helpful or even necessary. They are entitled to their opinion and entitled to argue it, but the rest of us who find them interesting and worthwhile, and there are a lot of us, should and will continue with business as usual.

Tuesday, February 15, 2011

January Best and Worst Case Scenarios

When it rains, it pours. It isn't strange for a week to pass without a poll, but sometimes it seems that they all try to get their say in at once. We had a "controversial" EKOS poll on Friday, a passed-around article from the Canadian Press on polling on Sunday, polls from Léger Marketing and Ipsos-Reid on Monday, and now today we have a poll released by Harris-Decima and a federal poll conducted for Newfoundland & Labrador by NTV. I also have two provincial polls I have to get to and a Newfoundland & Labrador by-election taking place tonight.

So, I need to get this out of the way before we pass into the second half of February. Yes, it's the January best/worst case scenarios!

These best and worst case scenarios calculate each party's best and worst projection results in each region.

For example, if the Conservatives had their best result in the western provinces in an Angus-Reid poll, their best result in Ontario in a Nanos poll, their best result in Quebec in a Léger poll, and their best result in Atlantic Canada in an EKOS poll, I would take each of these bests and combine them. And the same goes for a worst case scenario.

In other words, these projections are the best and worst possible results each party could have gotten had an election taken place last month, based on the available polling data.

These best and worst case scenarios are in terms of total seats only, and not necessarily about how a party would fit in with the others in Parliament.

January did not have a lot of polling, so in all of these best and worst case scenarios the ranges have narrowed, rather than expanded in any direction.

Let's start with the New Democrats. Their best case scenario would put them at 36 seats, exactly where they currently are in the House of Commons. With 19.6% of the vote, they would win 11 seats in British Columbia, none in Alberta, five in the Prairies, 13 in Ontario, two in Quebec, and five in Atlantic Canada.

But in this scenario the Conservatives and Liberals win about the same amount of seats as they have now, so that means no real change.

Their worst case scenario would reduce them to only 18 seats. With 13.1% of the vote, they would win three seats in British Columbia, none in Alberta, two in the Prairies, 12 in Ontario, one in Quebec, and none in Atlantic Canada.

This puts the NDP range at between 13.1% and 19.6% of the vote, and between 18 and 36 seats. Their December range was 12.4% to 24.1% and 15 seats to 40 seats. So, January's worst is better, but it's best is worse.

For the Liberals, their best case scenario in January still keeps them out of power. They would win 110 seats, 12 fewer than the Tories. But with the NDP they could outnumber the Conservatives.

With 31.4% of the vote, the Liberals would win 12 seats in British Columbia, two in Alberta, seven in the Prairies, 45 in Ontario, 15 in Quebec, and 27 in Atlantic Canada.

Their worst case scenario, however, would peg them at 76 seats. With only 24.1% of the vote, the Liberals would win four seats in British Columbia, none in Alberta, one in the Prairies, 40 in Ontario, 12 in Quebec, and 17 in Atlantic Canada. The Conservatives would win 143 seats, giving them as many as they currently have in Parliament.

The Liberal range has changed little from January. It is now between 24.1% and 31.4% of the vote, whereas it was between 23.9% and 32.4% in December. For seats, it has gone from 68-110 to 76-110. It gives them a better floor, but an election could still be dangerous.

For the Conservatives, their best case scenario is another minority government. They could only have won 146 seats in January, three more than they currently hold. With 37.3% of the vote, they would win 23 seats in British Columbia, 28 in Alberta, 22 in the Prairies, 54 in Ontario, eight in Quebec, and 10 in Atlantic Canada. The opposition would be unlikely to oust the government in such a situation.

For their worst case scenario, the Conservatives would still win the plurality of seats: 122. With 32% of the vote, the Conservatives would win 18 seats in British Columbia, 26 in Alberta, 19 in the Prairies, 49 in Ontario, four in Quebec, and five in Atlantic Canada. The Liberals and NDP would together win more seats than the Tories.

The Conservative range has narrowed significantly, to between 32% and 37.3% of the vote. In December, it was between 30.6% and 41.8%. In terms of seats, the range has gone from 117-162 in December to 122-146 in January. It makes it a bit of a safer bet for the Conservatives.

But with recent polls, it appears that January was far more calm than February will turn out to be.

Conservatives lead by 14 in new Ipsos-Reid poll

When the Conservatives criticized EKOS's most recent poll, Ipsos-Reid told Robert Fife of CTV that they were seeing the same things in their polling. Now released, the poll conducted for Postmedia News and Global Television shows an even wider lead for the Conservatives than in EKOS's poll.We last heard from Ipsos-Reid at the beginning of February, and since then the Conservatives have gained five points. They now lead with 39%. The Liberals, down four points, trail at 25%.

These gains are outside of the +/- 3.1 margin of error (19 times out of 20) for a random survey of this size, indicating that some real movement is taking place.

The New Democrats are up two points to 18%, while the Greens are steady at 10%. The Bloc Québécois is down two points to 9% nationally.

When we break down the national support numbers by age, we see a very close race in the 18 to 34 cohort: 26% for the Conservatives, 25% for the Liberals, and 23% for the NDP. But among those over the age of 34, the Tories hold a commanding lead. They are also in front among both men and women.

In Ontario, where the MOE for this survey is about five points, the Conservatives have gained six points and now lead with 42%. The Liberals are down eight to 32%, while the NDP is unchanged at 15%. The Greens, at 11%, are up three points. This is not dissimilar from the results EKOS found last week.

The Bloc Québécois has dropped five points in Quebec, but still leads with 37%. The Conservatives are up six points to 21%, echoing some better results we've seen for the Tories in recent polls. The Liberals and New Democrats are up one point a piece to 17% and 15%. All of these variations are within the 7% MOE for Quebec.

In British Columbia (MOE +/- 9%), the Conservatives are down three points to 39%. The NDP makes a big 13 point gain and now trails with 30%, while the Liberals are down two to 23%. The Greens, at 11%, are down four points.

The Conservatives are unchanged in Atlantic Canada (MOE +/- 14%) at 38%, followed by the Liberals at 31% (-3). The NDP is down four points to 18%, while the Greens are up seven to 13%.

In Alberta, the Conservatives are up nine points to 65%, pushing the Liberals down six points to 16%. The NDP is up three to 14%. All of these changes are within the province's 10% MOE.

Finally, in the Prairies (MOE +/- 13%) the Conservatives are up one to 43%, while the Liberals are at 24% (-6) and the New Democrats are at 23% (+4).

You may notice that I am rounding the margins of error for the regional results. This is because Ipsos-Reid (like most others) is rounding out their polling results. It just seems simpler, because technically a 42% result in Ontario for the Conservatives might mean 41.5% or 42.4%, making the extra 0.3 in the province's 5.3% MOE somewhat irrelevant.

With the results of this poll, ThreeHundredEight would project 18 seats for the Conservatives in British Columbia, 28 seats in Alberta, 20 in the Prairies, 60 in Ontario, 10 in Quebec, and 12 in Atlantic Canada for a total of 149. That is 20 more than were projected for Ipsos-Reid's last poll.

The Liberals would win seven seats in British Columbia, none in Alberta, five in the Prairies, 34 in Ontario, 12 in Quebec, and 17 in Atlantic Canada for a total of 77, 25 fewer than last time.

The Bloc Québécois would win 52 seats in Quebec.

The New Democrats would win 11 seats in British Columbia, none in Alberta, three in the Prairies, 12 in Ontario, one in Quebec, and three in Atlantic Canada for a total of 30, up 10 from last time.

Despite the 14-point national lead, the Conservatives do not reach the 155 mark needed for a majority. This might come as a surprise, but it shouldn't. In some regions of the country, the Conservatives are up against a ceiling. An improvement of three points in Ontario will not give the Conservatives more than nine seat gains, as projected for this poll. And note that, despite the overall increase in support nationwide, the party is still five points below their 2008 result in British Columbia, one point below in Quebec, and eight points below in the Prairies. To achieve their majority, the Conservatives cannot afford any losses in any part of the country.

Monday, February 14, 2011

Little change in Quebec in new Léger poll

A new Léger Marketing poll conducted for Le Devoir and the Montreal Gazette shows very little change in the provincial and federal voting intentions of Quebecers. But it appears that Liberals at both levels are losing clout in and around Montreal.Note that the provincial results are included below. Compared to Léger's last complete data set released in January, the Bloc Québécois has made a three-point gain in the province and now leads with 39%. The Liberals are up one to 20%, the New Democrats are steady at 19%, and the Conservatives have picked up one point and trail with 18%. The Greens have lost three points and are at only 3% in the province.

Léger uses an online panel for its polling, but their panel was randomly recruited by telephone. This sort of muddies the waters compared to other online panels that were not recruited in this way. But a random sample of 1,000 people would have a margin of error of +/- 3.1 points, 19 times out of 20. That means that at the provincial level none of the parties have had a statistically significant change in support.

There has been some noteworthy movement in and around Montreal, however. There, where the MOE is about five points, the Bloc has gained six points and now leads with 37%, well ahead of the Liberals. They are at 20%, down seven points from last month. The NDP is up three to 19% while the Conservatives are steady at 15%, but a small gain among non-francophones for the Tories leads one to believe that the Conservatives may be making up some ground on the Liberals in the anglophone parts of Montreal. The gap between the two parties is now eight points among non-francophones, representing a five point loss for the Liberals (36%) and a two point gain for the Conservatives (28%).

Among francophones, there has been very little change. The Bloc still leads with 46% (+2), followed by the NDP at 19% (unchanged), the Liberals at 16% (+2), and the Conservatives at 15% (unchanged).

One of things that will be worth watching in Léger's next monthly report will be the change of vote, if any, in the Quebec City region. Will the recent announcement of the building of a new arena in the city without the federal government's help change anything? Currently, the Conservatives are leading with 34% (-1), while the Bloc is a close second at 29% (+1). The NDP is steady at 21% while the Liberals are up one to 11%.

Finally, in the rest of Quebec the Bloc leads with 43%, down one point. The Liberals are up nine points to 21%, a gain out-pacing the MOE of +/- 6%. The NDP is down two to 18%, while the Conservatives are up two to 16%.

This would result in 52 seats for the Bloc Québécois, 14 for the Liberals, seven for the Conservatives, and two for the New Democrats.

Léger asked respondents in which leader they placed their confidence. Gilles Duceppe came on top with 29% (35% of those who responded with a name). Jack Layton came second with 27% (32%), while Stephen Harper (15%/18%) and Michael Ignatieff (8%/10%) followed. This is an indication of the NDP's potential for growth in the province, while also showing how the Liberals are limping along on brand-name only.

Among non-francophones, Layton is still in front with 26%, followed by Harper (21%) and Ignatieff (10%). That bodes well for the Tories' chances in the West Island.

Now to the provincial scene, where talk of the fictitious François Legault party has warped things out of all recognition.At the provincial level, we see no changes outside of the MOE. The Parti Québécois is down two to 34%, the Liberals are down one to 28%, and the ADQ is up one to 15%. Québec Solidaire has dropped one point to 9% while the Greens are unchanged at 7%.

But the other parties are up three points to 7%. I find it unlikely that all of that vote will go to the Marxists-Leninists or the Indépendantistes. If we pared that down to a more reasonable 2%, and distributed the other 5% proportionately, we'd get 36% for the PQ, 29% for the PLQ, 16% for the ADQ, and 10% for QS.

Among the two solitudes, there is no change greater than the MOE. The PQ leads among francophones with 40% (-3), trailed by the Liberals at 20% (-1) and the ADQ at 17% (+2). Among non-francophone, the Liberals are unchanged at 64%, while the Greens are up three to 15%.

As at the federal level, the Liberals have suffered a noteworthy drop in and around Montreal. There, the PQ leads with 36%, up two points. The Liberals are down seven to 21%, while the Greens are up one to 10%.

In Quebec City, the ADQ has dropped three points but leads with 36%, virtually mirroring the Conservative support in the region. The PQ is unchanged at 28%, while the Liberals are up three to 22%.

And in the rest of Quebec, the PQ has dropped six points to 33%, while the Liberals are up five to 26%.

This poll would result in 72 seats for the Parti Québécois, 37 for the Liberals, 14 for the ADQ, and two for Québec Solidaire. Generally, what we've been seeing for months.

Only 19% of Quebecers are satisfied with the government, and only 17% see Jean Charest as the best person to be Premier. That number is bumped up to 27% when we take out the 37% who had no response. Pauline Marois is at 19% (30% of "decideds), while Amir Khadir of QS is at 13%/21%, tied with Gérard Deltell. Like the NDP, QS appears to have some significant room for growth in Quebec, but unlike the federal scene it appears that the main sovereigntist party could suffer.

Sophomore MPs prove no easier to beat than veterans

With each election comes the promise of change. Voters can throw a government out, install a new one, or give those in power a new mandate to tackle the issues the country faces. Millions of dollars are spent, names are dragged through the mud, and, in the end, about four out of every five people we elected last time are sent back to Ottawa again.

The rest of the article can be read on The Globe and Mail website. The Hill Times study mentioned in the article can be found here.

I've been getting used to using the resources on the Elections Canada website, and have gotten quite fond of them. This is an incredibly useful site managed by the Parliament of Canada, and has electoral results stretching back to 1867.

I had approached this article with the intent of showing that veteran MPs are harder to knock off than sophomores. It seemed like an obvious hypothesis. But my analysis showed that there really isn't much difference between a four-term MP and a one-term MP.

You might be wondering why I didn't do a complete study of all 308 ridings. Time constraint is the reason, but my sample was representative. The re-election rate of incumbents in the 192 ridings I analyzed for 2006 and 2008 was only a tiny bit higher than the actual rate (89.1% to the actual 87.4%).

While looking into this, I also tracked other factors related to incumbency. I'll have to finish studying the ridings that remain and crunch some numbers, but it appears that in the vast majority of cases an incumbent's rate of increase or decrease in vote share from one election to the next is less than that of the incumbent's party in the region as a whole. If this turns out to be the case, it will be useful for my projections. The test I am running on the new projection model is good, out-performing other methods of projecting, but seems to be hung-up on over-achieving incumbents. With the results of this analysis I think I will be able to achieve a higher rate of accuracy. More to come when I have completed my tests.