Archived Seat Projections
Conservatives Edge Upward Among Mixed Regional Trends
The following seat projection is based upon a blended and weighted sample of polls released in February and conducted by Abacus, CROP (Quebec only), Ekos, Ipsos Reid and Leger Marketing among an aggregate sample of over 12,000 respondents. Results indicate only modest changes from the January LISPOP projection in any given region, and trends that are somewhat conflicting with each national party gaining support in some regions and declining in others. However cumulatively, the Conservatives gained the most in terms of potential seats (notably in British Columbia) and the New Democratic Party declined the most. One additional observation worth reporting is that in Quebec, Ekos is repeatedly finding greater incidence of Conservative support than do the other polling firms, perhaps a result of their sampling frame. From now on, LISPOP projections will be accompanied by an interactive map reflecting our estimate of the status of each of the 338 new federal constituencies. Map can be viewed at http://lispop.ca/elections/fed2015.html
Projected distribution of seats by party and region compared with actual election results (in brackets), released March 5, 2015
Other |
|||||
Canada | 140(166) |
122(34) |
72(103) |
3(4) |
1(1) |
Atlantic provinces | 5(14) |
24(12) |
3(6) |
-- |
-- |
Quebec | 10(5) |
29(7) |
36(59) |
3(4) |
-- |
Ontario | 57(73) |
48(11) |
16(22) |
-- |
-- |
Prairies & North | 18(26) |
7(2) |
6(3) |
-- |
-- |
Alberta | 31(27) |
2(0) |
1(1) |
-- |
-- |
British Columbia | 19(21) |
12(2) |
10(12) |
-- |
1(1) |
Note:
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.