Latest national poll median date: October 20
Projections reflect recent polling graciously made publicly available by pollsters and media organizations. I am not a pollster, and derive no income from this blog.

Monday, October 21, 2019

Projection by Region

Here are some details of the final projection by region. I will pick one riding per region where either I am skeptical of the projection, or that will be interesting to watch tonight.

Atlantic Canada (32)
LIB - 18.8 (19 projected ahead), 38.5%
CON - 9.0 (9), 28.6%
NDP - 4.1 (4), 19.7%
GRN - 0.1 (0), 10.2%
Riding where I don't believe the projection: Acadie--Bathurst. The NDP's severe organizational problems in NB are not reflected in the model, as there was no breakout of NB in any poll since August.

Québec (78)
BQ - 35.3 (39), 31.3%
LIB - 31.6 (30), 32.1%
CON - 8.7 (7), 15.7%
NDP - 1.8 (1), 12.5%
GRN - 0, 4.1%
Riding where I don't believe the projection: Saint-Maurice--Champlain. Minister François-Philippe Champagne has a high profile in QC and has spent a lot of time with the people of his riding. I expect him to survive.

Ontario (121)
LIB - 64.9 (68), 38.5%
CON - 44.3 (43), 33.9%
NDP - 11.7 (10), 18.7%
GRN - 0, 5.8%
Riding to watch: I have trouble picking since there are so many...

Manitoba/Saskatchewan (28)
CON - 19.9 (20), 48.4%
LIB - 5.0 (6), 21.9%
NDP - 3.1 (2), 3.1%
GRN - 0, 3.7%
Riding to watch: Regina--Wascana. Long-time MP and Liberal Minister Ralph Goodale could be threatened. He survived in 2011 when things were much worse for the Liberals overall, but this year, there is anger in SK, and the Conservative leader is from a neighbouring riding. How much will the NDP vote rally around him?

Alberta (34)
CON - 32.2 (33), 62.4%
NDP - 1.4 (1), 15.5%
LIB - 0.4 (0), 16.4%
GRN - 0, 2.6%
Riding to watch: Edmonton Strathcona. This is the one projected NDP seat, though I think the model is probably too sanguine in terms of margin of victory. A Mainstreet poll this week was publicly described as showing a very tight race.

British Columbia (42)
CON - 18.5 (18), 32.8%
NDP - 11.8 (13), 25.0%
LIB - 9.9 (9), 27.1%
GRN - 1.1 (1), 11.3%
Riding to watch: Nanaimo--Ladysmith. This isn't just a two-way NDP/Green race, but actually a three-way NDP/Green/Tory race. If the NDP and Greens split the left-wing vote evenly, the Conservative candidate could squeak by. This is also where the limitations of my shortcut for estimating probabilities of victory are apparent: Green MP Paul Manly obviously has a better than 10% chance of holding this riding, but his probability of victory is being underestimated due to being in third place.

FINAL 2019 Projection: \o/

The following polls have been added to the model:
Mainstreet's 10/19-20 national poll (current weight among national polls: 30%)
Research Co's 10/18-20 national poll (current weight among national polls: 9%)
EKOS' 10/17-20 national poll (current weight among national polls: 11%)
Forum's 10/18 national poll (current weight among national polls: 3%)
Nanos' 10/19 and 10/20 national polls (national results only; current weight among national polls: 6% and 18% respectively)
I have also updated ON regional adjustments using the breakdown from Campaign Research's 10/16-20 national poll, as well as Atlantic Canada and BC regional adjustments using the breakdown from Innovative Research's 10/15-17 national polls.
For a full list of included polls, see previous Projection posts.

And I'm finally done! This projection update includes polls that are favourable to the Liberals (EKOS, Forum) and polls that are negative for them (Mainstreet, Nanos). Because the latter have more weight thanks to their recency and sample sizes, the projection moves against the Liberals.

As you can see, the final projection gives an insignificant edge to the Liberals, which is flipped from the "quickie" projection I posted on Twitter just after the final poll was released. The Liberals gained roughly 1 seat, at the expense of the NDP. What accounts for the difference?
- In order to avoid Nanos and Mainstreet being the only polls with a midpoint date after Oct. 19, I used the Oct. 19-20 roll-up from the EKOS poll, and inferred Oct. 17-18 results, which were included as a separate poll. This slightly increases the weight on EKOS, which helps the Liberals and hurts the Tories. (As it turns out, the inferred results were given a weight below 0.5% by the model, so it doesn't matter if they're slightly off.)
- Updates to regional adjustments for BC, ON and Atlantic Canada help the Tories and Liberals and hurt the NDP and Greens.

Projection as of the latest national poll (midpoint: October 20)
LIB - 133.2 (32.1%)
CON - 132.7 (33.6%)
BQ - 35.3 (7.1%)
NDP - 34.5 (18.1%)
GRN - 1.2 (5.9%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Without the turnout adjustment, the projection would be:
LIB - 134.2 (31.6%)
CON - 126.0 (32.1%)
NDP - 39.1 (19.1%)
BQ - 36.1 (7.1%)
GRN - 1.4 (6.9%)
IND - 0.7
PPC - 0.6

I very crudely estimate the confidence intervals of the projection as follows:
80% confidence intervals
LIB 95-175
CON 95-170
BQ 20-50
NDP 15-50

95% confidence intervals
LIB 85-190
CON 85-185
BQ 15-55
NDP 12-55

Seats changing hands since the last projection:
- In NL, LIBs get St. John's South--Mount Pearl back from the NDP.
- In NL, CONs regain Avalon from LIBs.
- In PE, CONs regain Egmont from LIBs.
- In QC, the BQ regains Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix from CONs.
- In QC, the BQ regains Saint-Maurice--Champlain and Argenteuil--La Petite-Nation from LIBs.
- In ON, CONs regain Peterborough--Kawartha from LIBs.
- In ON, the NDP regains Oshawa from CONs.
- In MB, the NDP gets Elmwood--Transcona back from CONs.
- In BC, CONs regain Cloverdale--Langley City from LIBs.
- In BC, the NDP retakes Nanaimo--Ladysmith from GRNs.

Below is a map showing the seat-by-seat leading party. Please keep in mind that my projection uses riding polls only if they are not behind a paywall - i.e. very few riding polls outside QC are used. Moreover, I only take into account factors described in my methodology description. So I am tying one hand behind my back - no "the NDP isn't winning Acadie--Bathurst because of their organizational problems in NB and because this year's candidate does not share a last name with long-time MP Yvon Godin."


As you can see, the Liberals have a 5-seat lead in ridings projected ahead. The sums of probabilities are roughly equal because the Liberals win more tight races. Below are the 75 ridings where the gap between the top two parties is less than 5%:


A gap of less than 5% means that there is at least a 30% chance that the projected winner won't actually win. I expect to get almost half of these ridings (say, 30-35 out of 75) wrong.

Next, here are the 55 ridings where the gap is between 5% and 10%:


In "standard" two-way races, these projections should be correct 70-85% of the time. However, in three-way races, the probability of error significantly increases. This is also the case in special situations, such as the Territories, for which we don't have any polling. Therefore, I would expect to get 15-20 of these wrong.

Of the remaining 208 ridings, the standings are:
91 CON
82 LIB
20 BQ
14 NDP
  1 GRN
Of these:
- 56 have a gap between 10 and 16 points (85-95% chance of being correct in a standard two-way race),
- 58 have a gap between 16 and 22 points (95-99% chance of being correct), and
- 94 have a gap above 22 points.
Therefore, I would expect to get 10-15 of these wrong. Adding up the expected numbers of mistakes, there should be 55-70 of them; in other words, I expect 79-84% accuracy on an average night. If the polling averages are right, accuracy will likely be slightly higher, while if there is a significant polling error, then accuracy could be slightly lower.

Here's a potential pre-Speaker seating chart of the House of Commons:


Sunday, October 20, 2019

Trends 2019: Seventh and Final Instalment

For new readers: these trends are different - and I would say more meaningful - than the ones you might see elsewhere, since they are retroactively recomputed* when old data becomes available. Thus, my "Trends" posts avoid showing "fake" variations caused by polls coming out with different lags. More details were provided in the first instalment of this series. My post on comparing models highlights other advantages of my approach.

As I work on my final projection (considering adjustments based on some sub-regional breakdowns from Campaign Research and IRG), here is the final trends post. As usual, all numbers in this post reflect my turnout adjustment of CON +1.5, LIB +0.5, NDP -1, GRN -1.


Methodological note: The data points for September 26, October 3 and October 11 are not plotted: each of those dates was the midpoint of only one public national poll (Nanos tracker), making those projections less reliable given that discounting has become very aggressive.

1. The major story of the final week of the campaign was a steep further rise of the NDP, peaking at 40 seats and 19% national support on Monday/Tuesday, followed by an equally steep pull back, to 31-32 seats and under 17% on Friday/Saturday. However, the final NDP number is back up to the mid-30s and 18.2%: the last two polls (by median date) showed the NDP either not dropping from its mid-week levels (Mainstreet) or actually surging on the final day (Nanos). If the momentum that Nanos picked up is real and continues on Election Day, the NDP could approach, or even surpass its 2015 seat count of 44. However, if the final polls just happened to see noise on Sunday and a few tight races don't go the NDP's way, it could easily end up in the 20s.

Either way, it'd be a much better result than envisaged at the start of the campaign, when the NDP was hovering around 15 seats. Will Jagmeet Singh continue to perform well once the election is over, or will he prove as ineffective as he was before the campaign?

2. The Liberals appeared to have turned things around at Thanksgiving. They hit rock bottom a day or two before Thanksgiving, and have been on an upward creep since, except for the final day polls. Were strategic considerations making their way into voters' minds? If the final day downtick was noise and/or their turnout matches the Tories', the Liberals should eke out a win. If both are true, they should win comfortably. And if in addition, the IVR pollsters are right about Ontario so that the Liberals win it by ~10 points instead of 5, they may start thinking about a majority. If, on the other hand, the Tories beat the polls significantly like in 2011, the NDP gains more Liberal voters, and the Bloc's supporters, who tend to be older, turn out in droves - i.e. the perfect storm against Liberals - the Grits could fall dangerously close to 100.

If the Liberals win the most seats, it will probably be because some soft voters, having not seen any other plausible option (those in ON possibly being turned off the Tories by Doug Ford), reluctantly came home. Given the country's relatively good economic performance in the past few years, it seems likely that Trudeau has been a net drag on his party's fortunes this year.

3. The Tories fell through Thanksgiving weekend, though there appears to have been a modest recovery in the last few days. The general trend of the past month has been ugly for them. One cannot help but feel that, with just an average-quality leader, the Tories would have capitalized on Trudeau's baggage and be on their way to at least a strong minority - strong enough that Trudeau would probably feel obliged to resign. Indeed, that would be the case if the Tories just held their constant August level of 36%. Unlike for the Liberals, it is hard to see the Tories getting a majority because they are so far behind in QC. Even if they somehow tie the Liberals in both ON and Atlantic Canada and get above 20 seats in BC, they'd probably still need 20 seats in QC, which is just not happening. On the other hand, it is not difficult to imagine the Tories failing to make substantial gains: one just needs the IVR pollsters to be right in ON and the Tories dropping some tight races in the Atlantic and BC.

4. The Bloc's explosive rise appeared to stop just before Thanksgiving, and its support has held steady this week. It's looking like a seat count in the 30s for them if the tossups don't all fall one way or another. The main risk for the Bloc is that a significant fraction of its supporters actually approve of the Liberal government. If these voters decide to "play it safe" after all, the Liberals could hold up surprisingly well and avoid significant losses in QC, which would limit the Bloc to picking up NDP seats and getting in the 20s. On the other hand, Quebecers like to jump on bandwagons; if the Bloc capitalizes on that, it could well crack 40.

5. As I've commented in every (or almost every) trends post since the first one in late August, the Greens are on a downward track. Last week, I ventured that the Greens could fall below their 2008 popular vote of 6.78%, and it looks like that will be really close. At this point, it's all about saving Nanaimo--Ladysmith for them - gains are still possible, but they would be gravy. Just like Trudeau and Scheer, May needs to go.


*Changes made on or after Sept. 25 are only reflected back to the start of the campaign (Sept. 11). These include the re-weighting of standalone regional polls (i.e. regional numbers not part of a national poll), the Guilbeault baseline adjustment in Laurier--Sainte-Marie and fixing an old spreadsheet error. These only make a barely visible (if at all) difference on the graphs.

Mapped Projection Update: Campaign Research 10/16-20, Abacus 10/17-19, Ipsos 10/17-19

The following polls have been added to the model:
Campaign Research's 10/16-20 national poll (current weight among national polls: 35%)
Abacus' 10/17-19 national poll (current weight among national polls: 13%)
Global News Ipsos' 10/17-19 national poll (national and BQ results from Global News article only; current weight among national polls: 17%)
I have also considered the following polls for a potential update to ON regional adjustments, but no change was made:
Nanos' 10/7-13 ON breakdown
Léger's 10/10-14 GTA poll
For a full list of included polls, see previous Projection posts.

Taken together, these polls show a fairly static race between the Tories and Liberals. Abacus and Ipsos show the NDP losing some ground. Abacus has the Bloc up significantly since its last poll, but since that poll is over a week old and other polls have shown a Bloc increase since then, this does not shift the projection much. Abacus also has the Liberals jumping out to a lead in BC, but Ipsos shows them falling further behind, so there is still no clarity there (though Ipsos BC numbers cannot be included in the projection).

Accordingly, the NDP is slightly down in the projection, which is mostly stable.

Projection as of the latest national poll (midpoint: October 18)
LIB - 137.8 (32.4%)
CON - 133.0 (33.7%)
BQ - 34.0 (7.1%)
NDP - 30.4 (16.9%)
GRN - 1.8 (6.7%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, CONs get Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix back from the BQ.
- In ON, LIBs get Cambridge and Peterborough--Kawartha back from CONs.
- In ON, CONs get Oshawa back from the NDP.
- In MB, CONs regain Elmwood--Transcona from the NDP.
- In BC, GRNs retake Nanaimo--Ladysmith from the NDP.

Here is, belatedly, the map that I promised for last night. Of course, the map will be updated again when I post the final projection tonight!

Projection Update: Léger 10/17-18 and Nanos 10/17-19

The following polls have been added to the model:
Léger's 10/17-18 national poll (current weight among national polls: 14%)
Nanos' 10/17-19 national poll (national results only; current weight among national polls: 30%)
For a full list of included polls, see previous Projection posts.

Update Oct. 20: Added the Nanos regional breakdown for yesterday (with imputed values for MB/SK and AB) that were publicly released. (Earlier version of this post had just the QC and BC numbers discussed on CTV.)

Even though its headline is a national tie, the last Léger poll is rather bad news for the Liberals:
- Reduced lead in ON
- Bloc still increasing in QC (contrary to what most other polls show)
- Lost lead to Tories in BC
Even worse, this Léger poll's QC breakdown shows a reversal from the Léger megapoll of QC in that the Liberal vote seems to be increasingly concentrated in Montreal again. It's possible that the Liberals dropped more in the Montreal area to the NDP last week, but is getting some of those voters back. Or this could be noise. In any case, the QC adjustments have been revised. (I still need to work on the ON ones, though I will probably wait for the final Campaign Research poll for that.)

The Nanos poll is also bad news for the Liberals, who relinquish their national lead from yesterday. Nanos should have another release tonight with today's data though, so stay tuned.

All this bad news for the Liberals sends the projection back to a virtual tie.

Projection as of the latest national poll (midpoint: October 18)
LIB - 134.6 134.9 (32.1%)
CON - 133.1 132.8 (33.5%)
BQ - 34.0 (6.9%)
NDP - 33.4 (17.5%)
GRN - 1.7 (6.8%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, the BQ takes Richmond--Arthabaska, Trois-Rivières, Beauport--Limoilou and Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix from CONs.
- In QC, LIBs retake Outremont from the NDP.
- In ON, CONs retake Peterborough--Kawartha and Cambridge from LIBs.

Saturday, October 19, 2019

Projection Update: Campaign Research 10/16-19

The following poll has been added to the model:
Campaign Research's 10/16-19 national poll (current weight among national polls: 48%)
For a full list of included polls, see previous Projection posts.

Today's Campaign Research update adds about 1,500 respondents to the 2,000-respondent poll published yesterday. This update did not change the numbers much: the Tories and Liberals are up marginally, while the NDP and Greens are down marginally. Accordingly, the two main parties make small gains in the projection at the expense of the NDP and Bloc.

Projection as of the latest national poll (midpoint: October 17.5)
LIB - 139.1 (32.2%)
CON - 130.9 (33.0%)
NDP - 33.0 (18.0%)
BQ - 32.2 (6.9%)
GRN - 1.7 (6.6%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, CONs retake Trois-Rivières, Beauport--Limoilou and Richmond--Arthabaska from the BQ.
- In SK, CONs regain Saskatoon West from the NDP.

Projection Update: Mainstreet 10/16-18 and Riding Polls, QC Regional Adjustments

The following polls have been added to the model:
Mainstreet's 10/16-18 national poll (national results only; current weight among national polls: 19%)
Mainstreet's 10/? Québec poll
Mainstreet's 10/15 Vancouver Granville poll
Mainstreet's 10/16 Laurier--Sainte-Marie poll
Moreover, within-QC adjustments were updated using Léger's 10/13-15 QC poll. (Nanos' 10/4-13 QC breakdown and Forum's 10/11 QC poll were also considered, but were much less useful.)
For a full list of included polls, see previous Projection posts.

First, the main lesson from Léger's megapoll of QC is that the Liberal vote is slightly less concentrated in Montreal than was the case earlier during the campaign. This could be because Liberal losses to the NDP came disproportionately in Montreal. The Liberals are surprisingly competitive in Eastern QC, which is good news for someone like Minister of National Revenue Diane Lebouthillier. These regional adjustments push the Liberals up 0.5-1 seat in the projection, at the expense of the BQ and Tories.

The Mainstreet tracker shows a small Liberal increase at the expense of the NDP, Greens and BQ. In the projection, however, it is the NDP that profits: Mainstreet's anti-NDP lean means that just by staying at a high level (even with a small drop), the NDP impresses the model. At the same time, the modest Liberal increase in the poll was mostly priced in. The Bloc, Greens and Tories are down very slightly (under 1 seat each).

All three riding polls resulted in adjustments, though the ones for Vancouver Granville and Laurier--Sainte-Marie are inconsequential, as the difference between the top two candidates is almost unaffected. However, for Québec, the adjustment flips the riding, pushing Minister Duclos ahead by a few points.

Net effect of all this? Liberals and NDP gain about one seat each, Tories and Bloc lose about one seat each. Underwhelming, I know...

Projection as of the latest national poll (midpoint: October 17)
LIB - 137.1 (32.2%)
CON - 129.2 (33.0%)
NDP - 35.3 (18.0%)
BQ - 33.7 (6.9%)
GRN - 1.6 (6.6%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

I'm mostly caught up now, except for considering the following information for within-ON adjustments: Campaign Research's ON breakdown, Nanos' ON breakdown and the Léger GTA poll. (I will not be adding the Lethbridge College AB poll: due to its age, it would only have a ~1% weight in the AB average, not shifting any party's number by more than 0.1%.) This will be done tonight, at which point I will post a mapped projection update.

Seats changing hands since the last projection:
- In QC, the BQ takes Richmond--Arthabaska, Beauport--Limoilou and Trois-Rivières from CONs.
- In QC, LIBs get Avignon--La Mitis--Matane--Matapédia, Gaspésie--Les Îles-de-la-Madeleine, Québec and Saint-Maurice--Champlain back from the BQ.
- In QC, the BQ retakes Laurier--Sainte-Marie and La Prairie from LIBs.
- In QC, the NDP retakes Outremont from LIBs.
- In SK, the NDP gets Saskatoon West back from CONs.

Projection Update: Nanos 10/16-18, Insights West 10/13-16 BC Poll

The following polls have been added to the model:
Nanos' 10/16-18 national poll (national results only; current weight among national polls: 19%)
Insights West's 10/13-16 BC poll
Mainstreet's 10/9 Jonquière poll
For a full list of included polls, see previous Projection posts.

Nanos has some good news for the Liberals this morning, with the Grits gaining a point, the Tories losing a point, and the NDP also down slightly. The only issue for the Liberals is that the Bloc also jumped: Nanos now finally has it above 30%, even as other pollsters have it down from a few days ago.

This update also incorporates regional adjustments based on Insights West's BC poll. Because that poll does not give decided+leaning numbers, it does not figure in the projection average (manually distributing them is unreliable due to weighting issues). However, it is used to update sub-BC adjustments, which resulted in the Tories gaining about 0.5 seats at the expense of the NDP. The MB/SK breakdown from yesterday's Campaign Research poll was also used to update the MB/SK adjustments. This was also marginally positive for the Tories and negative for the NDP.

Finally, I've finally gotten around to adding Mainstreet's Jonquière poll, which resulted in a riding adjustment making a Bloc win only marginally less certain.

I'm now finally working on incorporating the following information from this week: Léger fine sub-QC breakdown, Campaign Research's ON breakdown, Nanos QC and ON breakdowns, Léger GTA poll and Forum QC breakdown. Today's public riding polls will also be added later.

Somewhat surprisingly, the projection did not move much. It appears that the good news for the Liberals was mostly pre-empted by yesterday's Campaign Research poll, which had the same field dates.

Projection as of the latest national poll (midpoint: October 17)
LIB - 136.2 (32.1%)
CON - 130.2 (33.0%)
BQ - 34.7 (6.9%)
NDP - 33.9 (17.5%)
GRN - 1.8 (7.1%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In ON, LIBs get Peterborough--Kawartha back from CONs.
- In SK, CONs regain Saskatoon West from the NDP.

Friday, October 18, 2019

Projection Update: Innovative 10/15-17, Campaign Research 10/16-18

The following polls have been added to the model:
Innovative's 10/15-17 national polls (current weight among national polls: 13% and 8%)
Campaign Research's 10/16-18 national poll (national results only; current weight among national polls: 36%)
For a full list of included polls, see previous Projection posts.

Note #1: This post will be updated later with the ridings where the lead changed. The regional breakdown on the left will also be updated at that time.

Note #2: I have not yet incorporated Campaign Research's sub-regional breakdowns into the projection, and I am aware of Insights West's BC poll. I'm also behind on adding the following information released earlier in the week: Léger fine sub-QC breakdown, Nanos QC and ON breakdowns, Mainstreet Jonquière poll, Léger GTA poll and Forum QC breakdown. I hope to have an update tonight where I catch up on all this...

Overall, the IRG polls were fairly neutral for the LIB/CON race: both parties lost equal ground relative to previous IRG polls. The Campaign Research poll helps the Liberals, who pull into a national tie and a 4-point lead in ON. These polls are not great news for the NDP: the smaller IRG poll has a very low NDP number, while Campaign Research has it down 1 point from last week.

As a result, the Liberals are up in the projection, while the NDP is down. After both flirting with 40 seats, both the NDP and Bloc are back down in the mid-30s. The Liberals move back to where they were on October 8, and are once again ahead of the NDP in MB/SK, AB and BC.

Projection as of the latest national poll (midpoint: October 17)
LIB - 135.9 (32.2%)
CON - 130.2 (33.2%)
NDP - 34.8 (17.7%)
BQ - 34.2 (6.9%)
GRN - 1.8 (6.9%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, the PPC retakes Beauce from CONs.
- In QC, the BQ retakes Longueuil--Charles-LeMoyne from LIBs.
- In QC, LIBs retake Outremont from the NDP.
- In ON, LIBs get Davenport, Toronto--Danforth, Parkdale--High Park and Nickel Belt back from the NDP.
- In ON, LIBs get Burlington, Vaughan--Woodbridge and Cambridge back from CONs.
- In BC, CONs retake South Okanagan--West Kootenay from the NDP.

Projection Update: EKOS 10/15-17, Mainstreet 10/15-17

The following polls have been added to the model:
EKOS' 10/15-17 national poll (current weight among national polls: 18%)
Mainstreet's 10/15-17 national poll (national results only; current weight among national polls: 27%)
For a full list of included polls, see previous Projection posts.

Today's EKOS poll is good news for the Tories. Relative to the last EKOS poll 3 days ago, they reduce the gap in Atlantic Canada and ON, and get a moderate lead in BC. The Liberals get good news in QC, while the NDP momentum appears to have stopped across the board. The Greens gain nationally, but, unfortunately for them, not in BC.

The Mainstreet tracker shows a Tory uptick and a Green downtick from yesterday, with other parties relatively stable.

Unsurprisingly, overall, the Tories gain in the projection, retaking a marginal lead. Has their two-week-long bleeding finally stopped? The Liberals and Bloc are down marginally.

Projection as of the latest national poll (midpoint: October 16)
CON - 131.9 (33.1%)
LIB - 130.2 (31.3%)
NDP - 39.8 (19.1%)
BQ - 33.4 (6.7%)
GRN - 1.5 (6.6%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs retake Laurier--Sainte-Marie and Longueuil--Charles-LeMoyne from the BQ.
- In ON, CONs regain Vaughan--Woodbridge and Burlington from LIBs.
- In SK, CONs regain Desnethé--Missinippi--Churchill River from the NDP.
- In AB, CONs get Edmonton Griesbach back from the NDP.
- In BC, CONs retake Pitt Meadows--Maple Ridge from the NDP.

Projection Update: DART 10/16, Nanos 10/15-17, Léger 10/13-15 QC Poll

The following polls have been added to the model:
DART's 10/16 national poll (current weight among national polls: 25%)
Nanos' 10/15-17 national poll (national results only; current weight among national polls: 22%)
Léger's 10/13-15 QC poll
For a full list of included polls, see previous Projection posts.

Note: I have not yet incorporated the Léger fine sub-QC breakdown into the projection. I'm also behind on adding the following information released earlier in the week: Nanos QC and ON breakdowns, Mainstreet Jonquière poll, Léger GTA poll and Forum QC breakdown. I hope to have an update this evening where I catch up on all this...

Today's DART poll shows little change from last week. It helps the Tories in the projection not because it shows a 4-point Tory national lead (the model accounts for DART's Tory lean), but because:
- the Tories are flat from last week, while other pollsters show them down, and
- the Tories swapped votes in AB for votes in ON.
This poll basically offsets the Forum poll conducted on the same day, released yesterday afternoon: taken together, those two polls have essentially no impact on the projection.

The Nanos tracker is mostly flat, except for a small Tory drop, consistent with other pollsters. Adding the Léger QC poll also had little impact, as its results are very similar to the QC polling average.

Projection as of the latest national poll (midpoint: October 16)
LIB - 131.3 (31.1%)
CON - 129.1 (32.5%)
NDP - 40.0 (19.0%)
BQ - 34.7 (6.8%)
GRN - 1.8 (7.4%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get La Prairie and Châteauguay--Lacolle back from the BQ.
- In ON, CONs retake Newmarket--Aurora, Whitby, King--Vaughan, Richmond Hill, Peterborough--Kawartha and Cambridge from LIBs.
- In ON, the NDP retakes Davenport from LIBs.

Thursday, October 17, 2019

Projection Update: Forum 10/16

The following poll has been added to the model:
Forum's 10/16 national poll (current weight among national polls: 31%)
For a full list of included polls, see previous Projection posts.

This Forum poll is the first one of the campaign with the Tories below 30% both nationally and in a public ON breakdown. They are also well behind the leading Liberals in the Atlantic and the 3rd place NDP in QC. It's just one poll, but the trend has been extremely negative for the Conservatives - consistently losing 1 point every 4 days since the start of October - and this merely shows that trend continuing.

The NDP is now ahead of the Liberals in the polling average in both BC and AB, in addition to MB/SK. The Liberals, on the other hand, are back up to 70 seats in the ON projection.

Projection as of the latest national poll (midpoint: October 16)
LIB - 134.0 (31.4%)
CON - 124.6 (32.3%)
NDP - 41.1 (19.6%)
BQ - 35.7 (6.9%)
GRN - 1.5 (6.6%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get Argenteuil--La Petite-Nation back from the BQ.
- In ON, LIBs get King--Vaughan, Whitby and Newmarket--Aurora back from CONs.
- In ON, LIBs get Davenport back from the NDP.
- In AB, the NDP retakes Edmonton Griesbach from CONs.
- In BC, the NDP takes Pitt Meadows--Maple Ridge from CONs.

Projection Update: Mainstreet 10/14-16

The following poll has been added to the model:
Mainstreet's 10/14-16 national poll (national results only; current weight among national polls: 47%)
For a full list of included polls, see previous Projection posts.

This Mainstreet update has the Liberals up a point from yesterday, with the Greens still dropping. The Bloc is also slightly lower - the Liberals must hope that this continues.

Projection as of the latest national poll (midpoint: October 15)
LIB - 131.3 (31.3%)
CON - 127.8 (32.7%)
NDP - 39.6 (18.8%)
BQ - 36.6 (7.1%)
GRN - 1.6 (6.9%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection: this will be updated later, along with the provincial breakdown in the left column.
- In ON, LIBs get Richmond Hill back from CONs.
- In SK, the NDP retakes Desnethé--Missinippi--Churchill River from CONs.

Projection Update: Nanos 10/13-16

The following poll has been added to the model:
Nanos' 10/13-16 national poll (national results only; current weight among national polls: 29%)
For a full list of included polls, see previous Projection posts.

This Nanos update has all parties' vote shares changing by 0.2% or less, except the Liberals, who drop by a still small 0.4%. Accordingly, the projection shows marginal change. The NDP drops slightly because the model was expecting a bigger NDP increase in the Nanos tracker given yesterday's Mainstreet poll (whose recency is between yesterday's and today's Nanos polls due to Nanos skipping Thanksgiving).

Projection as of the latest national poll (midpoint: October 14.5)
CON - 130.4 (33.0%)
LIB - 129.8 (31.0%)
NDP - 38.4 (18.4%)
BQ - 36.6 (7.0%)
GRN - 1.7 (7.4%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection: none.

Wednesday, October 16, 2019

Projection Update: EKOS 10/11-15

The following poll has been added to the model:
EKOS' 10/11-15 national poll (current weight among national polls: 14%)
For a full list of included polls, see previous Projection posts.

A new EKOS poll is out, and like in other polls, there is a large NDP increase and also a Bloc increase from last week. However, EKOS shows the Tories and Liberals also marginally up. Of course, there must be a loser, and it's the Greens - this poll is a total disaster for them.

Regionally, the Liberals are showing strength in ON with a big lead, while the NDP is doing well in BC, placing a very strong second. What this means is that even though the Tories, Liberals and NDP all gain the vote share projection, the Tories are down again in terms of seats, falling below 130 for the first time.

Projection as of the latest national poll (midpoint: October 14)
LIB - 130.1 (31.1%)
CON - 128.9 (32.8%)
NDP - 39.3 (18.6%)
BQ - 36.9 (7.1%)
GRN - 1.6 (7.2%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In PE, LIBs get Charlottetown and Egmont back from CONs.
- In QC, CONs retake Beauce from the PPC.
- In QC, CONs get Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix back from the BQ.
- In ON, LIBs get Peterborough--Kawartha back from CONs.
- In ON, the NDP retakes Davenport from LIBs.
- In SK, CONs retake Desnethé--Missinippi--Churchill River from the NDP.
- In AB, CONs get Edmonton Griesbach back from the NDP.
- In BC, the NDP gets South Okanagan--West Kootenay back from CONs.

Projection Update: Mainstreet 10/13-15

The following poll has been added to the model:
Mainstreet's 10/13-15 national poll (national results only; current weight among national polls: 43%)
For a full list of included polls, see previous Projection posts.

Today's Mainstreet poll shows a further NDP increase, with a Green drop and a smaller Tory decrease. The NDP is now approaching the 40-seat mark in the projection, and, in terms of the popular vote, in close range of the second-place Liberals in both AB and, more importantly, BC (as remarked earlier, the NDP is already ahead of the Liberals in MB/SK).

Projection as of the latest national poll (midpoint: October 14)
CON - 130.5 (32.6%)
LIB - 129.4 (31.0%)
NDP - 38.3 (18.4%)
BQ - 36.9 (7.1%)
GRN - 1.9 (7.7%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, the BQ retakes Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix from CONs.
- In QC, the NDP retakes Outremont from LIBs.
- In ON, the NDP retakes Toronto--Danforth from LIBs.
- In ON, LIBs get Cambridge back from CONs.
- In SK, the NDP gets Desnethé--Missinippi--Churchill River back from CONs.
- In AB, the NDP regains Edmonton Griesbach from CONs.
- In BC, the NDP retakes Nanaimo--Ladysmith from GRNs.

Projection Update: Nanos 10/12-15 and Mainstreet 10/9 Trois-Rivières Poll

The following polls have been added to the model:
Nanos' 10/12-15 national poll (national results only; current weight among national polls: 20%)
Mainstreet's 10/9 Trois-Rivières poll
For a full list of included polls, see previous Projection posts.

Update Oct. 16: Corrected minor spreadsheet error.

This Nanos update has all parties' vote shares changing by 0.5% or less, so of course the projection changes little. This is the first Tory increase in the projection after six straight drops, and it is the fifth in a row with the Liberals stubbornly flat, between 129 and 130 seats.

The Mainstreet Trois-Rivières poll causes a riding adjustment that shifts a net 0.3 seats from the Bloc to the Tories.

Projection as of the latest national poll (midpoint: October 13.5)
CON - 132.4 132.9 (32.9 33.0%)
LIB - 129.7 129.4 (31.0%)
BQ - 36.4 36.5 (7.0%)
NDP - 36.3 36.1 (17.7 17.6%)
GRN - 2.1 (8.1 8.2%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, CONs retake Trois-Rivières and Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix from the BQ.
- In QC, LIBs get Outremont back from the NDP.
- In AB, CONs get Edmonton Griesbach back from the NDP.
- In BC, GRNs retake Nanaimo--Ladysmith from the NDP.

Tuesday, October 15, 2019

Projection Update: Angus Reid 10/12-15

The following poll has been added to the model:
Angus Reid's 10/12-15 national poll (current weight among national polls: 39%)
For a full list of included polls, see previous Projection posts.

Note: I have not updated the provincial seat distribution table on the left due to lack of time.

Today's Angus Reid poll is quite similar to last week's, so the projection shifts little. The Tories are very low in AB and the Liberals in Atlantic Canada, but that's probably just due to the small sample sizes (fewer than 150) in those areas. The Bloc widens its still insignificant lead in QC, while the Liberals erase the Angus Reid Tory lead in ON. The Conservatives have fallen back in BC, within range of both the NDP and Liberals, while the Greens' single-digit result in BC has them fall to 2.0 seats in the projection.

Projection as of the latest national poll (midpoint: October 13.5)
CON - 131.2 (32.9%)
LIB - 129.6 (30.9%)
BQ - 37.2 (7.0%)
NDP - 36.9 (17.8%)
GRN - 2.0 (8.2%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection: No time to update - sorry!
- In PE, CONs regain Egmont and Charlottetown from LIBs.
- In ON, LIBs get Toronto--Danforth back from the NDP.
- In AB, the NDP gains Edmonton Griesbach from CONs.
- In BC, the NDP takes Nanaimo--Ladysmith from GRNs.

Projection Update: Mainstreet 10/12-14 and Forum 10/11 QC Poll

The following polls have been added to the model:
Mainstreet's 10/12-14 national poll (national results only; current weight among national polls: 51%)
Forum's 10/11 QC poll
For a full list of included polls, see previous Projection posts.

Note: I have not yet reviewed QC sub-regional adjustments based on the Forum poll's breakdown. The results of the review will either be provided in an update to this post or rolled into a future update.

Today's Mainstreet tracker shows a Conservative drop, along with small increases for the NDP and Bloc again. The projection shifts accordingly.

The Forum QC poll shows the Liberals and Bloc both up from the QC subsample of the Forum poll conducted immediately after the English debate, at the expense of the other parties. Are some Quebecers realizing that it's a two-way race in most of the province, and picking a camp accordingly?

Projection as of the latest national poll (midpoint: October 13)
CON - 132.2 (32.9%)
LIB - 129.4 (30.9%)
BQ - 37.0 (7.0%)
NDP - 35.7 (17.8%)
GRN - 2.4 (8.2%)
IND - 0.7
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, the BQ gains Beauport--Côte-de-Beaupré--Île d'Orléans--Charlevoix from CONs.
- In QC, the BQ gains La Prairie and Argenteuil--La Petite Nation from LIBs.
- In ON, the NDP regains Toronto--Danforth from LIBs.
- In ON, LIBs get Mississauga--Lakeshore, Kitchener South--Hespeler, Vaughan--Woodbridge and Burlington back from CONs.

Projection Update: Ipsos 10/11-13 and Mainstreet's Sherbrooke Poll

The following polls have been added to the model:
Global News Ipsos' 10/11-13 national poll (national and Bloc QC results from Global News article only; current weight among national polls: 30%)
Mainstreet's Sherbrooke poll
For a full list of included polls, see previous Projection posts.

There is no Nanos update today due to Thanksgiving yesterday, but we do have the weekly Ipsos poll, which confirms what other pollsters have shown: an NDP rise pulling from both the Tories and Liberals, but more from the latter. Interestingly, contrary to other pollsters, Ipsos does not show the Bloc gaining further ground from the consortium debates, but the Bloc does hold all of its gains from the TVA debate. As this poll was almost exactly in line with expectations, the projection barely moves at all.

An update to the Sherbrooke adjustments has also been made, as a result of which the Bloc's lead in the riding is reduced. Moreover, Liberal and Conservative numbers from ON and QC from yesterday's Mainstreet poll were added - this hurts the Liberals in QC.

Projection as of the latest national poll (midpoint: October 12)
CON - 135.5 (33.5%)
LIB - 129.3 (30.9%)
BQ - 35.6 (6.8%)
NDP - 33.9 (17.4%)
GRN - 2.5 (8.2%)
IND - 0.7
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Note: The NDP is ahead of the Liberals in MB/SK. This actually flipped in the last projection when I imputed MB/SK numbers from the Nanos 10/11-13 Prairies figures, but I had swapped the two numbers in the regional vote share table.

Seats changing hands since the last projection:
- In QC, the PPC retakes Beauce from CONs.
- In QC, the BQ gains Laurier--Sainte-Marie and Châteauguay--Lacolle from LIBs.
- In ON, the NDP regains Parkdale--High Park from LIBs.
- In ON, LIBs get Oakville back from CONs.
- In BC, LIBs get Cloverdale--Langley City back from CONs.

Monday, October 14, 2019

Projection Update: Mainstreet 10/11-13

The following poll has been added to the model:
Mainstreet's 10/11-13 national poll (national results only; current weight among national polls: 50%)
For a full list of included polls, see previous Projection posts.

Today's Mainstreet poll shows the Liberals partly closing the gap with the Tories, with the NDP flat and the Bloc slightly up, relative to the last public release on Friday. The effect on the projection, however, is negative for the Liberals. This is somewhat surprising, but can be explained by the following:
- The BQ level is high relative to other pollsters' surveys last week, so the lack of mean reversion is good news for the Bloc: perhaps Mainstreet got another BQ-friendly sample, but perhaps this new sample isn't particularly BQ-friendly, and the Bloc's rise has continued. And of course, a Bloc increase mainly hurts the Liberals seat-wise.
- The NDP level doesn't look particularly high, but given Mainstreet's tendency to produce low NDP numbers, it is interpreted as high by the model. Then, for much the same reason as for the Bloc, the NDP remaining flat is taken as good news for it. This hurts both the Liberals and the Tories, but the former more than the latter.

As a result, the NDP and Bloc are both up, with other parties - but mainly the Liberals - down.

Projection as of the latest national poll (midpoint: October 12)
CON - 137.6 (33.8%)
LIB - 129.5 (31.0%)
BQ - 34.2 (6.6%)
NDP - 33.2 (17.3%)
GRN - 2.4 (8.0%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

(I have also imputed some MB/SK and AB numbers for yesterday's Nanos release, instead of leaving those fields blank as Nanos only gives numbers for the "Prairies." This helps the Tories in the Prairies but hurts them a little elsewhere since the model adjusts regional polling averages so that they add up to the national one. The net effect is tiny, however: well under 1 seat.)

Seats changing hands since the last projection:
- In NL, the NDP gains St. John's South--Mount Pearl from LIBs.
- In QC, the BQ gains Montmagny--L'Islet--Kamouraska--Rivière-du-Loup from CONs.
- In QC, the BQ gains Québec, Shefford, Saint-Maurice--Champlain and Longueuil--Charles-LeMoyne from LIBs.
- In ON, the NDP regains Nickel Belt from LIBs.
- In MB, the NDP gets Elmwood--Transcona back from CONs.
- In SK, the NDP gets Saskatoon West back from CONs.
- In BC, CONs regain Cloverdale--Langley City from LIBs.
- In BC, the NDP gains Burnaby North--Seymour from LIBs.

Projection Update: Nanos 10/11-13

The following poll has been added to the model:
Nanos' 10/11-13 national poll (national results only; current weight among national polls: 52%)
For a full list of included polls, see previous Projection posts.

Happy Thanksgiving!

Today's Nanos poll is 2.5 days more recent by midpoint date than the next most recent freely available poll (excluding, of course, the Nanos releases from the past 2 days), Abacus' 10/8-11 survey. To put things in perspective, more time has elapsed between the 1st and 2nd most recent polls than between the 2nd and 11th most recent ones! This means that free public data really doesn't yet contain much information about where things stand this weekend. Because the projection is for the situation as of the most recent poll: (i) it puts (uncomfortably) high weight on the Nanos poll, and (ii) there is much greater uncertainty surrounding it than usual. The effective sample size for a projection is usually around 3000, and had increased to about 6000 a few days ago due to the deluge of polls. Now, it is down to around 1600.

So did Nanos pick up any meaningful movement from yesterday? Nope. The Liberals are up slightly, and the Bloc and NDP are down slightly, but there's basically no change. As a result, the projection is essentially flat (although the NDP does take 3rd place by an entirely insignificant margin). Sorry for the anti-climax!

Projection as of the latest national poll (midpoint: October 12)
CON - 138.2 (33.9%)
LIB - 134.6 (31.6%)
NDP - 30.8 (16.4%)
BQ - 30.7 (6.3%)
GRN - 2.7 (8.6%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get Québec back from the BQ.
- In BC, LIBs get Cloverdale--Langley City back from CONs.

Sunday, October 13, 2019

Trends 2019: Sixth Instalment

For new readers: these trends are different - and I would say more meaningful - than the ones you might see elsewhere, since they are retroactively recomputed* when old data becomes available. Thus, my "Trends" posts avoid showing "fake" variations caused by polls coming out with different lags. More details were provided in the first instalment of this series. My post on comparing models highlights other advantages of my approach.

By now, you've probably heard that the Liberals have essentially lost their seat edge. How did we get here? It's time for another trends post! As usual, all numbers in this post reflect my turnout adjustment of CON +1.5, LIB +0.5, NDP -1, GRN -1.


Methodological note: The data points for September 26 and October 3 are not plotted: each of those dates was the midpoint of only one public poll (Nanos tracker), making those projections less reliable given that discounting has become very aggressive. October 11 would also fall into this category, but I've plotted it since it's the last date available.

1. Both the Liberals and the Conservatives have lost over 3 points from their campaign highs, which occurred just before "blackface" for the Grits and just after it for the Tories.
- For the Conservatives, the fall happened in three phases: coming off the immediate post-blackface high, Andrew Scheer's rough week with resume-gate and dual-citizenship-hypocrisy-gate, and then the debates.
- For the Liberals, "blackface" cost about 1.5 points on impact, but the Scheer pre-debate struggles helped them recover a good chunk of the lost ground. However, Jagmeet Singh's good performance in Monday's English language debate proved even more costly than "blackface" for the Liberals: around 2 points and 20 seats lost, essentially overnight.
- For both parties, the situation may be stabilizing, but the truth is that after an avalanche of polls with an Oct. 9 midpoint date, there were few with an Oct. 10 or Oct. 11 one. So the stabilization you see on the graphs is very preliminary, and may be a mirage.

2. The NDP had been creeping up throughout the campaign, but was mostly just regaining the ground lost during its disastrous pre-writ period. What has happened since the English debate, however, is another story: an impressive 3-point jump essentially overnight, drawing from both the Liberals and Tories.
- As many have mentioned, trends starting at this point in the campaign just amplified in the final week in 2011 and 2015. However, there is a crucial difference from 2011 and 2015: back then, the party heading up (NDP in 2011, Liberals in 2015) gained a lead over their main competitor, so strategic voting may have taken care of the rest. This time, the NDP remains well behind the Liberals, so strategic considerations would act in the opposite direction in most of ON, QC and parts of other provinces. This makes the trajectory of the final week very unpredictable.

3. The BQ's trend has been quite similar to the NDP's, and the seat projections for them have been essentially identical for the past 3 weeks.
- In the BQ's case, there is no strategic consideration that would cause its recently acquired supporters to turn away in the final week. Therefore, I would rate the odds of a significant pull back to be lower for the BQ than the NDP. However, the BQ is in a zone where its seat projection is very sensitive to its vote share, so even a minor pullback could push it back well below 30 seats.

4. If you have been following my "Trends" posts, you've probably noticed that I have consistently been bearish on the Greens, who keep heading down except during major external events (NDP pre-writ losses, "blackface," Greta's protests). Well, the past week has done nothing to change that: despite the big Liberal drop, the Greens are flat, possibly with any gains offset by losses to the NDP. Worse, the NDP is the Greens' main competitor in their Vancouver Island targets. Perhaps there will be some local effect that allows the Greens to nevertheless make several gains on the Island, but both the Esquimalt--Saanich--Sooke seat poll by Mainstreet and the September sub-BC breakdown by Insights West suggest nothing of the sort. The Greens are even at risk of falling short of their 2008 vote share!

There will be a final trends post next weekend, and possibly one mid-week if developments warrant it. Buckle up - this could be a wild ride!


*Changes made on or after Sept. 25 are only reflected back to the start of the campaign (Sept. 11). These include the re-weighting of standalone regional polls (i.e. regional numbers not part of a national poll), the Guilbeault baseline adjustment in Laurier--Sainte-Marie and fixing an old spreadsheet error. These only make a barely visible (if at all) difference on the graphs.

Mapped Projection Update: Abacus 10/8-11 and Nanos 10/10-12

The following polls have been added to the model:
Abacus' 10/8-11 national poll (current weight among national polls: 27%)
Nanos' 10/10-12 national poll (current weight among national polls: 37%)
For a full list of included polls, see previous Projection posts.

The Abacus poll shows only a modest NDP rise, and the Bloc increase is also smaller than in other polls, allowing the Liberals to keep a 12-point lead in QC. The Liberals fall into a tie with the Tories, but because the model already priced that in and because the Liberals actually expand their lead in ON, adding this poll was mildly positive for the Liberals.

The Nanos poll shows a considerable NDP increase and Liberal drop. This was likely mostly due to dropping Oct. 9, when I estimate Nanos still had the NDP in the mid-teens and the Liberals in the mid-thirties. It actually looks like Oct. 12 was not as good as Oct. 11 for the NDP (guess is 19% vs. 21%), so perhaps things are stabilizing. Of course, that could change again as Canadian gather for Thanksgiving...

But wait, there's more: Nanos' public PDF had the regional figures today! We see that Nanos still has a 10-point lead for the Liberals in ON. As a result, the addition of the Nanos poll is only mildly negative for the Liberals. The Grits come out marginally ahead considering both polls added, even though they trail by slightly more in the popular vote. The Bloc is down about a seat, while the Tories and NDP are flat.

Both these polls confirm that the NDP has vaulted ahead of the Greens in Atlantic Canada, and that BC is a three-way race with the Greens some distance behind.

Projection as of the latest national poll (midpoint: October 11)
CON - 139.1 (34.0%)
LIB - 133.2 (31.5%)
BQ - 31.4 (6.3%)
NDP - 30.6 (16.4%)
GRN - 2.6 (8.4%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get Shefford back from the BQ.
- In ON, LIBs get Markham--Stouffville, Mississauga--Streetsville and Kanata--Carleton back from CONs.
- In ON, LIBs get Nicket Belt back from the NDP.
- In BC, the NDP gets Port Moody--Coquitlam back from CONs.

Here are a map of the projection and a potential (pre-Speaker election) House of Commons sitting chart:

Saturday, October 12, 2019

Projection Update: Campaign Research 10/8-10

The following poll has been added to the model:
Campaign Research's 10/8-10 national poll (current weight among national polls: 17%)
For a full list of included polls, see previous Projection posts.

Note: This post will be updated after I review sub-regional adjustments using this poll's fine breakdown.
Update Oct. 13: I have now updated the subregional adjustments for ON and MB/SK based on this poll. I have also done the same for QC based on the breakdown (French only) for this week's Léger poll. The details of the adjustments can be found through this link.

Campaign Research has provided us with another large-sample poll, and it corroborates what other pollsters have seen this week: decreases for both the Tories and Liberals, and a surge by the NDP and Bloc. The only national difference is that the NDP surge is a bit more pronounced than in other polls. Accordingly, adding this poll to the projection helps the NDP a bit, but doesn't cause a big change.

Regionally:
- In Atlantic Canada, the NDP's strong showing and the Greens' weak showing in this poll allows the former to surpass the latter in the polling average for the first time in months.
- In QC, the Tories drop to 14%, their lowest level in any publicly released regional breakdown since I started tracking polls in the early summer - and probably for a long time before that. The all-important Liberal and BQ numbers are in line with the polling average.
- In ON, the Liberals eke out a 1% lead, compared to a tie in the last Campaign Research poll. However, the NDP at 20% will cost the Liberals in some Liberal-NDP races that are relevant again.
- In MB/SK, this is yet another poll showing the NDP challenging the Liberals for 2nd place.
- In BC, it's a three-way race between the Tories, NDP and Liberals. This poll is only the third public one placing the NDP (marginally) ahead of the Liberals since the start of the campaign (the others being DART 9/11 and EKOS 9/27-30). The Greens being 7 points behind the NDP is very problematic for them. The NDP is now back in the lead in all 5 of its Vancouver Island ridings.

Projection as of the latest national poll (midpoint: October 10)
CON - 138.6 139.3 (33.8%)
LIB - 132.6 132.0 (31.5%)
BQ - 31.7 32.4 (6.5%)
NDP - 31.2 30.4 (16.5%)
GRN - 2.8 2.7 (8.5%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In NB, the NDP gains Acadie--Bathurst from LIBs.
- In QC, the BQ regains Gaspésie--Les Îles-de-la-Madeleine from LIBs.
- In QC, the NDP retakes Outremont from LIBs.
- In ON, CONs regain Peterborough--Kawartha, Mississauga--Lakeshore, Oakville, Mississauga--Streetsville and Markham--Stouffville and  from LIBs.
- In ON, the NDP gains Oshawa from CONs.
- In ON. LIBs get Davenport, Toronto--Danforth and Parkdale--High Park back from the NDP.
- In ON, LIBs get St. Catharines back from CONs.
- In SK, the NDP gets Saskatoon West back from CONs.
- In BC, CONs retake Cloverdale--Langley City from LIBs.
- In BC, the NDP gets Courtenay--Alberni back from CONs.
- In BC, the NDP gets Esquimalt--Saanich--Sooke back from GRNs.

After adding the QC breakdown from this week's Léger poll, the following ridings changed hands:
- The BQ gains Avignon--La Mitis--Matane--Matapédia and Shefford from LIBs.
- CONs get Beauport--Limoilou back from the BQ.
- LIBs get La Prairie, Laurier--Sainte-Marie and Longueuil--Charles-LeMoyne back from the BQ.

Projection Update: Nanos 10/9-11 and Mainstreet 10/9 Beauce Poll

The following polls have been added to the model:
Nanos' 10/9-11 national poll (national results only; current weight among national polls: 26%)
Mainstreet's 10/9 Beauce poll
For a full list of included polls, see previous Projection posts.

First, please note that the last projection post was updated as, earlier this morning, DART released the full regional breakdown for its poll.

Today's Nanos finally shows some upward movement by the Bloc (which remains lower than in other polls), but the big news is that it shows the NDP increase amplifying. My guesstimate of daily Nanos numbers (not used in the projection) suggests that the NDP was at 21% last night, with the Liberals falling slightly below 30%, possibly a first since the start of the campaign. The Tories are also struggling, being not much above 30%.

However, as it turns out, the model had already priced in much of the NDP/BQ increases and Liberal/Tory decreases, so the projection moves very little, adding only 0.3% and 1 extra seat to the NDP.

The Beauce poll resulted in an update to adjustments that eliminates the slim Bernier lead in the projection, and makes this race a dead heat again. Note, however, that Bernier's subsequent solid French debate performance and decision to campaign in Beauce essentially for the remainder of the campaign may ultimately net him a few extra points.

Projection as of the latest national poll (midpoint: October 10)
CON - 138.6 (33.9%)
LIB - 134.4 (31.6%)
BQ - 31.7 (6.5%)
NDP - 29.2 (16.1%)
GRN - 2.9 (8.7%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get Gaspésie--Les Îles-de-la-Madeleine back from the BQ.
- In QC, CONs retake Beauce from the PPC.
- In ON, LIBs get Peterborough--Kawartha and Markham--Stouffville back from CONs.

Friday, October 11, 2019

Projection Update: DART 10/9

The following poll has been added to the model:
DART's 10/9 national poll (current weight among national polls: 10 12%)
For a full list of included polls, see previous Projection posts.

Note: This post will be revised if the full regional breakdown becomes available before the next projection update. Update Oct. 12: The full regional breakdown from DART is now available (link above updated). The Sun article had misreported the numbers in ON: it is the Liberals that have a 1-point lead there, with the NDP at 25% rather than 18%.

This DART poll has the NDP and Bloc higher than other recent polls. However, because this has typically been the case for DART, the projection is essentially unaffected by these results.

This is another poor poll for the Liberals in BC this week, reversing some good news for them here last week. On the other hand, the Tory lead Conservative Party, both nationally and in ON, has actually shrunk fallen by more than the Liberals relative to the last DART poll conducted in the immediate aftermath of "blackface."

Projection as of the latest national poll (midpoint: October 9)
CON - 139.2 139.6 (33.9 34.1%)
LIB - 134.3 134.0 (31.5 31.6%)
BQ - 31.7 32.0 (6.5%)
NDP - 28.3 (15.7 15.8%)
GRN - 3.2 3.0 (9.1 8.8%)
PPC - 0.6
IND - 0.6
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, the BQ gains Gaspésie--Les Îles-de-la-Madeleine from LIBs.
- In QC, the BQ gains Beauport--Limoilou from CONs.
- In ON, the NDP gains Toronto Danforth and Davenport from LIBs.
- In SK, the NDP gets Saskatoon West back from CONs.
- In BC, CONs regain Courtenay--Alberni from the NDP.

Projection Update: EKOS 10/7-10 and Mainstreet 10/8-10

The following polls have been added to the model:
EKOS' 10/7-10 national poll (current weight among national polls: 11%)
Mainstreet's 10/8-10 national poll (national results only; current weight among national polls: 22%)
For a full list of included polls, see previous Projection posts.

The new EKOS poll shows the Liberals dropping and the NDP and Bloc rising from 11 days ago, unsurprisingly. The Bloc is not as high as in other polls, but the last EKOS poll had them extremely low there, so increase is large. The Tories haven't fallen, but that may be due to them already being low in the previous EKOS poll. As usual, EKOS has the Greens very high, especially in BC.

The biggest change is that EKOS sees ON tightening dramatically, though as the article notes, the Liberals did better there later in the polling period.

The Mainstreet poll shows the Liberals dropping further from yesterday, with the NDP rising. Have the Tories reached a floor, so that further NDP gains would come almost only from the Liberals? The Bloc also keeps increasing.

Adding the Mainstreet poll had a mild effect on the projection: the Liberals lose 4 seats, and other parties make marginal gains. Then adding the EKOS poll had almost no effect on the aggregate projection, though as you can see in the seats changing hands, the poor Liberal number in ON flips a number of seats.

Projection as of the latest national poll (midpoint: October 9)
CON - 139.7 (34.2%)
LIB - 135.3 (31.7%)
BQ - 30.9 (6.4%)
NDP - 27.8 (15.6%)
GRN - 3.1 (8.9%)
PPC - 0.6
IND - 0.6
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In NS, the NDP gains Halifax and Sackville--Preston--Chezzetcook from LIBs.
- In QC, the BQ regains La Prairie from LIBs.
- In ON, CONs regain Markham--Stouffville, St. Catharines and Peterborough--Kawartha from LIBs.
- In ON, the NDP gains Nickel Belt and Parkdale--High Park from LIBs.

Projection Update: Nanos 10/8-10 and a Mainstreet Riding Poll

The following polls have been added to the model:
Nanos' 10/8-10 national poll (national results only; current weight among national polls: 14%)
Mainstreet's 10/5 Montmagny--L'Islet--Kamouraska--Rivière-du-Loup poll
For a full list of included polls, see previous Projection posts.

The Nanos poll shows the Liberals down and the NDP up. As I mentioned yesterday, it is likely that Oct. 7 was a good Liberal night in Nanos polling, so the Liberal decrease may not have been any real movement. The NDP increase, on the other hand, appears meaningful, but was expected given what other polls have already shown. Overall, the projection moves very little.

The riding poll resulted in adjustments that mostly eliminated the Tory lead in Montmagny--L'Islet--Kamouraska--Rivière-du-Loup, making it in danger of falling to the Bloc, with the Liberals within striking distance.

Projection as of the latest national poll (midpoint: October 9)
LIB - 139.7 (32.4%)
CON - 138.6 (34.4%)
BQ - 29.9 (6.4%)
NDP - 25.8 (15.0%)
GRN - 2.9 (8.7%)
PPC - 0.6
IND - 0.6
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection: none.

Thursday, October 10, 2019

Projection Update: Angus Reid 10/8-10 and Innovative 10/8-10

The following poll has been added to the model:
Angus Reid's 10/8-10 national poll (current weight among national polls: 35%)
Innovative's 10/8-10 national poll (current weight among national polls: 28%)
For a full list of included polls, see previous Projection posts.

The Angus Reid poll corroborates others: the two big parties are down, with the Bloc and NDP gaining. The notable regional result is a good Tory number in BC, with a decent sample size of 472.

The IRG poll, on the other hand, shows very similar numbers to IRG polls from earlier in the campaign, with the NDP even dropping a point. The only notable change has been an increase in the Bloc number, and even then, 26% is fairly low compared to most other polls conducted this week.

The Angus Reid numbers are roughly in line with what the model was expecting, given the firm's Tory lean. If this poll had been added alone, despite being weighted at 48% due to its big sample size and recency, the projection would have moved by less than 5 seats against the Liberals, with modest gains for the Tories, Bloc and NDP.

The IRG numbers are also roughly in line with what the model was expecting, given the firm's Liberal lean (in its non-ad-testing polls). The numbers are mildly positive for the Liberals: NDP and BQ are a bit lower than expected, but also the Tories haven't dropped.

What is the cumulative effect of these two polls? Despite these two polls being weighted at 63%, the projection moves by 0.4 seats or less for all parties! This is remarkable stability, considering that for the main parties, just a 1% shift would move several seats.

Projection as of the latest national poll (midpoint: October 9)
LIB - 139.0 (32.3%)
CON - 138.5 (34.3%)
BQ - 30.2 (6.4%)
NDP - 26.2 (15.0%)
GRN - 2.9 (8.7%)
PPC - 0.6
IND - 0.6
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get La Prairie back from the BQ.
- In QC, LIBs get Outremont back from the NDP.
- In ON, CONs regain Kanata--Carleton from LIBs.
- In ON, the NDP regains Hamilton East--Stoney Creek from LIBs.
- In BC, the NDP gets Victoria back from LIBs.

Projection Update: Mainstreet 10/7-9

The following poll has been added to the model:
Mainstreet's 10/7-9 national poll (national results only; current weight among national polls: 38%)
For a full list of included polls, see previous Projection posts.

Update Oct. 12: Fixed error in seats changing hands.

Today's Mainstreet tracker behaved quite differently from the Nanos one: the Liberals drop, the Bloc rises, and the Tories stay flat. The polls do agree about continued NDP momentum.

Mainstreet has also publicly released its regional breakdown. As was the case in earlier Mainstreet polling, the breakdown is friendly to the Liberals in ON and to the Tories in BC. The Greens also do relatively well in BC, and come a surprising second in Atlantic Canada (sample of 162).

As you might expect, the projection essentially reverts to what it was before the Nanos poll (though with the Liberals marginally ahead), except for a further increase by the Bloc. For the first time, both major parties are below 140. I don't have the Greens ahead in any Atlantic seat, but the expected value of their number of seats there is above 0.5 for the first time.

Projection as of the latest national poll (midpoint: October 8)
LIB - 139.4 (32.1%)
CON - 138.3 (34.5%)
BQ - 29.9 (6.3%)
NDP - 26.1 (15.2%)
GRN - 3.3 (8.7%)
IND - 0.6
PPC - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, the NDP retakes Outremont from LIBs.
- In QC, the BQ takes Abitibi--Baie James--Nunavik--Eeyou, Longueuil--Charles-LeMoyne, Québec, Laurier--Sainte-Marie, Sherbrooke and La Prairie from LIBs.
- In BC, CONs regain Steveston--Richmond East from LIBs.
- In BC, Wilson-Raybould retakes Vancouver Granville from LIBs.
- In BC, the NDP gets Courtenay--Alberni back from CONs.

Projection Update: Nanos 10/7-9

The following poll has been added to the model:
Nanos' 10/7-9 national poll (national results only; current weight among national polls: 26%)
For a full list of included polls, see previous Projection posts.

Today's Nanos poll partly corroborates what Léger and Mainstreet showed yesterday: a Tory drop and an NDP increase. However, in some encouraging news for the Liberals, Nanos shows a Liberal increase rather than a Liberal drop. In a sense, this Nanos poll balances out the quick Forum poll released on Monday, as Forum disagreed with Léger and Mainstreet on the Tories, while Nanos disagrees on the Liberals.

A note of caution, however: my guesstimate of the nightly results suggests that the dropped day (10/6) was moderately strong for the Tories, while the night that will be dropped tomorrow was a good one for the Liberals. So the Nanos tracker may tighten again tomorrow. However, guessing nightly results is a fraught exercise, so don't be shocked if tightening doesn't happen!

Obviously, as this poll balances out the Forum one, the projection moves back for the Liberals. This comes at the expense of all other parties - including the NDP because, although this poll corroborates its rise, it shows a smaller one than others.

Projection as of the latest national poll (midpoint: October 8)
LIB - 146.2 (33.0%)
CON - 137.8 (34.4%)
BQ - 26.1 (5.9%)
NDP - 23.9 (14.6%)
GRN - 3.0 (8.8%)
PPC - 0.6
IND - 0.5
If you're new to my 2019 projections, view key interpretive information here.

Seats changing hands since the last projection:
- In QC, LIBs get Longueuil--Charles-LeMoyne back from the BQ.
- In ON, LIBs get Kanata--Carleton back from CONs.
- In ON, LIBs get Hamilton East--Stoney Creek back from the NDP.
- In BC, LIBs get Steveston--Richmond East back from CONs.
- In BC, LIBs retake Vancouver Granville from Wilson-Raybould.