The following projection is based upon a series of polls released during the last half of July, 2019, by Nanos, Abacus, Angus Reid, Campaign Research, Leger, Forum and Mainstreet, producing a blended and weighted sample of approximately 12,400 respondents. The Liberal Party of Canada leads with 152 seats, followed by the Conservative Party of Canada with 142 seats. The New Democratic Party is projected with 23 seats, the Bloc Québécois with 13 seats, the Green Party with 6 seats, and one each for an independent candidate and the People’s Party of Canada. This is not to be interpreted as a prediction of the future, but rather is an estimate of what the parliamentary seat distribution may have looked like, if an election had occurred during the period of polling.
In no region of the country did changes in voter support since the previous projection (July 21) exceed the margin of sampling error. Collectively, the shifts did represent a modest gain for the Liberals. The region with the greatest change in projected seats was Ontario, where the estimated variation in popular vote only moved from a three-percentage-point to a five-point Liberal advantage over the Conservatives. However, with so many competitive ridings there, that swung five constituencies from the Conservatives to the Liberals. There are in fact over twenty Ontario ridings classified as "too close to call" because no party was estimated to have a vote lead of over five percentage points. Most of those are in the 905 area code region, the suburban ring surrounding the city of Toronto.
In Quebec, by contrast, the Liberal differential over the Conservatives rose by three percentage points, but that only translated into one seat change.
Liberal support actually declined in western Canada, but the party had hardly any seats there to lose.
The basic conclusion to be drawn from these data is that we are in minority government territory.
Table 1: Federal Seat projections - August 2019 (2015 election results in brackets)
|Canada||142 (99)||152 (184)||23 (44)||13 (10)||6 (1)||1||1|
|Atlantic||10 (0)||22 (32)||-||-||-||-||-|
|Quebec||12 (12)||50 (40)||2 (16)||13 (10)||-||1||-|
|Ontario||44 (33)||64 (80)||13 (8)||-||-||-||-|
|Prairies / North||24 (18)||6 (8)||1 (5)||-||-||-||-|
|Alberta||33 (29)||- (4)||1 (1)||-||-||-||-|
|British Columbia||19 (10)||10 (17)||6 (14)||-||6 (1)||-||1|
Note: The "regional swing model" is more fully explained in a paper presented by Dr. Barry Kay to the 2009 annual meeting of the American Political Science Association, entitled "A Regional Swing Model for Converting Canadian Popular Vote into Parliamentary Seats 1963-2008." It should be noted that the application of the model above does not make use of the "incumbency effect" described in that paper. In tests for past elections, using late campaign polls to project electoral outcomes, the model has proved to be accurate within an average of four seats per party since 1963. Readers interested in post-dictions for past federal elections dating back to 1963, for projections using pre-election polls dating back to the 1980 federal election and for three Ontario provincial elections, may contact me at firstname.lastname@example.org.