The Liberals are having a somewhat good start of the campaign, with the 1000-persons rally yesterday in Montreal. Of course, you could argue that the Conservatives are currently winning because they managed to focus everyone on the word coalition instead of talking about the wording of the non-confidence motion. But in any ways, polls have been harsh for the Liberals. On the other hand, the NDP is consistently projected high (around 19-20%). This constitutes a big change as compared to before the election where this party woud stand around 14-15%.
Yet today a little ray of hope with the release of this new Abacus poll. There is also a new HD poll, but we don't have the regional breakdown yet, so I won't use it for my daily-projections (but the HD poll is much more in line with the other recent polls though). Oh, and I saw this poll from Forum Research. I don't really remember this compagny. This one is actually saying a very different story than Abacus, with the Conservatives being at 41%! But since there isn't a regional breakdown provided (well, there is, online, if you subscribe and pay, so no thanks), I can't use it. It's too bad, I could have used the two polls to illustrate how to introduce some uncertainty in the model, something I'll talk about again very soon. If anyone has access to the regional details of the Forum poll, please let me know.
So back to the Abacus poll. That would give the projections displayed here (sorry no fancy picture for single-poll projections).
Yes, the Tories would still win, but would go back to a smaller minority. I know, I know, I said good news for the Liberals. But at that stage of the campaign, limiting Harper to 128 seats would already be an accomplishment for Ignatieff and his party. I'm not saying he'll not be able to increase his level of support substantially during the next 34 days, but for now, let's be realistic and use what we currently know.
But before any liberal fan gets high expectations, remember this is only one poll, going against the general trend and with a sample size of 1000 only. It means that some of the weird results in some provinces (the NDP at 33% in the Atlantic, while the CPC stands at only 24% there; the high Prairies score for the Liberals; etc) are probably due to a ridiculously small sample size.
Not that I want to talk about a coalition anymore (as a former sutdent in political science, I find it fascinating, but as a voter, I'm getting tired of it), but for the first time in a long time, the number of seats for LPC+NDP is actually higher than the CPC. Just saying...