Archived Seat Projections

Liberals Headed Towards Majority
A blending of polls collecting data from Nanos Research, Leger Marketing, Angus Reid and Ipsos Reid, which includes approximately 6000 respondents surveyed between Sept. 28-Oct.3, produces a popular vote distribution of Liberals 37%, Progressive Conservatives 32.5% and New Democratic Party 26%. That in turn when placed into the model produces the current seat projection that shows the Liberals on the cusp of a majority. In blending these polls, there is a challenge about how to weight the most recently collected data which really portray the change. Those familiar with the LISPOP model will know that the basic projection calculation is fixed, but the incorporation of polling data into the model can be arbitrary, particularly when public opinion is shifting. For the purposes of this projection, we continue to use polling data collected since Sept. 28 after the leaders' debate but the data since Oct. 1 show greater Liberal strength. If the totals are closer to the Ipsos figures, or if momentum continues to move toward the Liberals, the party could secure a majority of 60 seats with most of the difference coming from the PC party which could be stuck with seat totals similar to 2007. Either way, the NDP vote is also up substantially from 2007, and could see its seat count double in the Ontario legislature.

Projected distribution of seats by party, released October 5, 2011

2011 Projection
2007 Results
2007 Projection
Ontario PC Logo 2010.jpg


The "regional swing model" is more fully explained in a paper originally prepared and presented by Dr. Barry Kay to the 1990 annual meeting of the Canadian Political Science Association, entitled "Improving Upon the Cube Law: A Regional Swing Model for Converting Canadian Popular Vote into Parliamentary Seats". 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 bkay@wlu.ca.