Ok so I'm back from Mexico (it was really nice, thanks for asking). I looked at the projections and here are some comments.

1) Polls were underestimating the Conservatives.

While the polls were mostly right for the other parties, they clearly underestimated the Conservatives. If you take the last couple of polls published during the week-end, they all put the CPC around 35-37%. Given that these polls had a sample size of 2000-3000 most of the time (Ekos, Angus, Leger), it means the actual Tory score is out of the margin of error. Numbers can be even worse at the province-level. For instance in Ontario, you never had the Tories at 45% like they did on Election Day. Pollsters will (and already have in some cases like Ekos) have to revise how they survey people I think.

2) Atlantic

Using the actual percentages for this regions (which are, respectively for the CPC, LPC and NDP 37.9%, 29.3% and 29.5%), you would get 9 mistakes. Most are coming from the tricky NF-L. However, it seems that my assumption that some of the ABC effect was gone was right. Indeed, the Tories increased more in NF-L that in the rest of the Atlantic: they increased from 16.6% to 28.4%. But the effect wasn't 50% gone, more like 25% then. With that being said, weird things happened anyway. The only riding won by Harper was Labrador and unless I wasn't aware of a new star-candidate, it was definitely not the most likely to switch. In the rest of the Atlantic, the model performed quite well.

3) Quebec

The big orange wave. It's funny, with my final projections, Iw as the harshest on the Bloc (as compared to 308 or DS) and I was a little bit worried to underestimate this party... Boy I actually overestimated them. Even by using the actual percentages, I would still have the Bloc with 10 seats. I would have the Liberals at 12, but winning 6 out of 7 close races. Therefore a more adjusted projections would be 9-10. The same for the Tories with 9 seats but 5 out of 6 clsoe races, leading to adjusted results of 7. By the way, if you actually compare the close races projected to be won by the Liberals over the NDP to the actual results, you see that the model was actually quite close most of the time, instead that the NDP won these ridings slightly. Having the correct "call" is important, but being accurate is as well.

The model would have worked quite well in Quebec everywhere except in Gaspésie where the NDP won almost everything while the model was still giving most of the ridings to the Bloc. It's because historically, the Bloc was more resilient there and the NDP's swing was clearly decreased there. With that being said, th Bloc ending up with only 4 seats despite finishing second in the popular vote with as much as 23% is puzzling. I would actually be worried to have my model correctly predicting that! lol I mean, it seems the Bloc was caught in a wave AND was freaking unlucky on top of that.

4) Ontario

Ok here I need to mention something first. The following comparisons are made using a simplified model that I had. As for Quebec, I had other models ready for Ontario in case all parties would enter extrapolation-territories. Since the final polls were showing the NDP around 25%, Liberals around 27% and, most importantly, the Conservatives slightly down compared to 2008, I decided to use the full model, and not the simplified, more extrapolation-friendly one. BUT, if the polls had shown the CPP at 45%, I would have switched to the other model. People reading this blog regularly know that I have many specifications. After all, I did switch for Quebec after the orange wave started.

So anyway, no matter which model I would have used, my projections would have have been mostly ok in Ontario, except in the GTA. There is no way to reconcile historical trends and what we saw last Monday. In particular, while the provincial swings explain how the Tories won ridings in the suburbs of Toronto, they shouldn't have won seats in Toronto. For instance, the seat of Ignatieff should have remained a Liberal one. Historically, the Tories swing was decreased in Toronto. Look at the following table:

		04 to 06				06 to 08
	CPC	LPC	NDP		CPC	LPC	NDP
east905	3.3%	-4.0%	1.0%		6.8%	-10.1%	-0.7%
west905	4.1%	-3.9%	0.2%		3.8%	-5.5%	-0.8%
Tor. east	4.0%	-3.1%	0.5%		2.5%	-4.7%	-1.3%
Tor. West	3.3%	-3.8%	1.0%		3.9%	-5.4%	-1.0%
prov. swing	3.6%	-4.8%	1.3%		4.1%	-6.1%	-1.2%

As you can see, traditionally, the Tories were increasing a little bit less in this region while the Liberals were holding up better (except in the east 905 where the Tories already had all but one seats since 2008). So ridings liks the one from Ignatieff where the difference between the Tories and the Liberals was more than 11-points were not likely to switch when the provincial swing for the Tories was +5 and -8.5 for the Liberals. You have a lot of ridings in this situations where the provincial swings were actually amplified for both parties! What it means is that there was a major change occuring in the GTA during this election. Maybe it actually all makes sense. I mean, yes traditionally the LPC was holding up better, but now that the Liberals were already low everywhere but in the GTA, it kind of makes sense that any further drop province-wide would have to come from the GTA! I'll think about it while building the next model. In any way, I was very clear that my model was probably not appropriate for extrapolation purposes. For this, simplistic model assuming an uniform swing (or a proportional one) as better suited.

5) What to do next?

My objectives has always been to turn such a model into a published paper. Now that we have more data (and in particular, I now have variation for the NDP, a party that used to move very little and was tricky to estimate), I will be able to test various specifications more in details. I couldn't do that before because, in order to estimate the coefficients, I need more elections. Indeed, with only 3 (2004 to 2008) and thus 2 swings, I hadn't enough data points. Now, I can use data from 2004 to 2008 to see how I could have explained 2011 better. One thing I'll have to try to make the model more extrapolation-friendly. With a majority government, I have more time to do that! I'll keep you posted with the updates.

Doing seat projections is always tricky. You can go simple and be right sometimes, but sometimes you are wrong. In 2008, for the Quebec election, my model was the only one to predict 7 ADQ MLAs instead of the 2-3 predicted everywhere else. Why? Because I had regional coefficients. But when the regional patterns change, like this time in Quebec (Gaspésie) or in the GTA, a model based in historical patterns would necessarily be wrong. Seat projection is not an exact science. However, I still think there is a place for a scientific, complicated and transparent model like mine.

I'll also be back for the next Quebec election, around 2012 I guess. I don't know yet if I'll have time to build a model for Ontario or BC.

Ok so Harper won his majority. Why were the predictions wrong?

Well, if you excude the Atlantic where I would have to look more in-depth into it, it's mostly the fact that the Tory vote was underestimated by most polls. This is especially true in Ontario. If you enter the actual percentages in the model, you get results much closer to the actual ones. I understand this is a lame excuse but it at least shows that the conversion % to seats wasn't that wrong. And it also shows that it's important to provide a simulator like I do. It allows people to use the percentages they believe are right (i.e: correcting the polls).

As for the predictions, I was the hardest model on the Bloc, so yea I guess... For Quebec, surprisingly, except in Gaspésie and a little bit in Montreal (Mostly Mtl-East), the model wasn't that bad for the NDP.

The collapse of the Liberals is way worse than predited in the polls. This is crazy.

I'll look at the details results next week, when I'm back. In the mean time, congratulations to DemocraticSpace who was the only model to predict a majority even though it was a smaller one. On the other hand, DS, was more off than me for the Bloc and NDP.

Thanks to Louis-Benoit L'Italien-Brunot, here is a map of the final projections. It's very nice.

By the way, I'm slow for answering comments because I'm currently in... Mexico! I left yesterday. Yes yes I know, so unprofessional for a seat projecter lol But I couldn't leave later because I start teaching next Monday and my girlfriend couldn't leave earlier... So we voted in advanced polling and we booked a resort with wifi. Hey, if NDP candidates can do that (and even get a chance to be elected), I sure have the right to do the same! lol

So I'll reply today. I have to say, no matter the results, it was a pleasure running this site and having all your comments and suggestions. I'll do this for sure during the next elections.

Here we are, the final projections! So let's answer the big question first: Stephen Harper and the Conservatives are projected to win this election, but only with another minority. So the big wish of Harper to finally get his majority is not projected to happen. It could still happen (look at the total safe+100% all races for the Tories), but it will all come down to Ontario. It's way more likely to be another minority. Thus the official call of this site.

The second big news is the NDP finishing second, thanks to a big surge in Quebec as well as, to a lesser extent, in the rest of Canada. Jack Layton is projected to become the leader of the opposition surely. Will he be the PM within the next 3 months? Maybe, it all depends on two things. First, how will Harper react to another minority? Will he try to reach out to the opposition or not? Also, will the Liberals support the NDP or the Tories? I would say that a big factor in this equation is whether NDP+LPC have the majority. But all this is beyond the basic objective of this website and will not be resolved until weeks.

For the Liberals and the Bloc, it's like a race for the biggest collapse. For the Grits and Michael Ignatieff, this election could well be remembered as the equivalent of 93 for the Tories (although, I'm not saying the Liberals will only elect two MPs)! They have no chance to win this election and are even out of reach of the second place.

As for the Bloc, for the first time since this party exists, it will almost surely finish second in Quebec! And not only in the number of votes as in 2000 (when the Liberals finished first), but also in the number of seats. This is historic. In the worst case scenario, Gilles Duceppe could even lose his seat and/or be the leader of only 10 MPs. Please notive that the projection of 14 seats is probably too harsh. Indeed, the Bloc is projected to win only 4 out of 20 close races. It's too low, the Bloc should probably be projected around 19 seats. And Liberals and CPC should be a little bit lower in la Belle Province.

So let's go region by region.

1. Atlantic Canada.

It was a source of a lot of potential gains for the Tories at the beginning of the campaign. However, recent regional polls, as well as some polls conducted in specific ridings in NF-L, tend to show that the Tories won't make many gains there. Remember that my model take into account the fact that the regional swing for the each party has two components: the ABC effect and an actual regional swing. That could be very important to predict the numbers of seats won by each party outside of NF-L. Indeed, imagine everything is the same except that the ABC is gone. That would result in a regional lead of 6-points for the Tories! But if you don't adjust for the fact that this increase is entirely in NF-L, you'll overestimate the Tories everywhere else, in particular in IPE.

In this region, the party who is actually likely to make gains is the NDP which was projected to finish first in many last minute polls. Finishing first in the Atlantic won't likely give Jack Layton the majority of the seats in this region (mostly because of the large majorities a lot of Liberals in incumbent had in 2008), but would boost the numbers of MPs from 4 to potentially 8.

2. Quebec.

Ok let's be clear here: this province will likely be completely crazy. I worked very hard on my model for this province, trying many specifications, in order to be as correct as possible in the context of a possible historic orange wave. At the end, my projections are favourable to the NDP but less than a pure uniform swing model. If you compare my projections to the ones from Ekos for instance (which uses, I'm sure, a uniform swing), you'll see the Bloc and Liberals higher and the NDP a little lower. While I completely believe the NDP will finish first in this province, I think it will fall short of a total sweep where the Bloc would fall to 10 seats or less. However, no matter the specification of the model used, the number of seats won by the NDP vary a lot depending on whether this party gets 37% or 40% of the votes (and alternatively, whether the Bloc gets 25 or 28%). So it could really go either way, but I choose the medium one. You can see the high volatility in the 95% CI.

3. Ontario.

This is the key of a possible Tory majority. Actually, it is really the only place where it can happen. As I said, the Atlantic is unlikely to provide Harper with enough seats, while the CPC will probably be happy to lose only 3 seats in Quebec! In Ontario, the potential gains are mostly in the GTA, in particular in the suburb of Toronto (in the west 905). However, the Conservatives have been polled around 41% (+2 compared to 2008) consistently during the entire campaign. This provincial swing would probably not be enough to secure enough gains. Yes the CPC might shift its support to the GTA, but that would then mean they would be down somewhere else in the province. Given the surge of the NDP, that could well result in some losses. So the overall net gains will, in all likelihood, not be enough to reach a majority (the Tories basically need to win 65-70 seats in this province). One way it could happen is if the NDP "only" reaches 23% and the Liberals fall to 28%. That scenario would lead to a lot of vote splitting and give some seats to the Tories.

4. Prairies/Alberta.

I haven't covered these regions very much during this campaign. But I had a good reason: we haven't seen much change in the polls. The Conservatives will surely win a large majority of the seats over there. Will they make any gains? Maybe some riding, but the overall results should be, at best, very similar to 2008. The NDP could even make gains there. This party will also likely keep its only Alberta riding.

5. British Columbia.

The Tories already won 22 of the 36 ridings in 2008, so they don't have that many potential gains. With the NDP polled close second in some recent polls, the only hope for the Tories is to steal some seats from the collapsing Liberals. For instance Vancouver South where the Liberals incumbent won by only 21 votes last time. However, the Conservatives candidate got into a lot of troubles during the campaign. On a personal note ( I live in Vancouver Kingsway but I drive a lot in Van South), I would say I saw more Liberals sign this time around than in 08. So I think the Liberals will lose some seats, but not all of them. In any ways, Harper just can't really count on BC to get a majority, not with the NDP so high.

Also, Elizabeth May is projected to lose her riding but it will be a close race. I actually wouldn' be surprised if she won, mostly thanks to a heavy campaign from the Green and a lot of Liberals voters switching. Her "boost" might be even bigger than estimated using the 2006 by-election and the Nova-Scotia run of 2008 (I "boost" her by 20-points in the model, more than any other candidate).

Here is the pdf. Enjoy the election!

Here it is, more details to come later today, with the latest Ekos poll. ou'll have a riding-by-riding pdf with the min/max of each party in each riding.

But in the mean time, you have the official call of this site: Tories minority, NDP official opposition.

Here is the pdf.