However, I decided to take a look at the average gap between polls of ten Canadian polling firms and the poll average calculated by the 338Canada model. I used every publicly available poll (from this list) since January 2017. For each poll, I subtract the poll average from the score for each party. Results are then tabulated and the average "skew" is calculated for each firm.
Overall, 108 polls were considered:
- 22 polls from Nanos Research (one per every four weeks as to not use duplicate data);
- 17 polls from Forum Research;
- 15 polls from Campaign Research;
- 13 polls from Ipsos;
- 12 polls from Abacus;
- 8 polls from Mainstreet Research;
- 7 polls from Angus Reid;
- 6 polls from Léger;
- 4 polls from EKOS
- 4 polls from Innovative Research;
Here are the results for the Liberals (x-axis) and the Conservatives (y-axis).
Nanos Research, Campaign Research and Abacus Data are the closest to the centre, but all firms are pretty much located within a radius of three points from the average... with the notable exception of Forum Research. Indeed Forum measures the CPC on average more than six points higher than the poll average.
That's a considerable gap.
What about the NDP? Here is the graph of the Liberals (x-axis) and the NDP (y-axis):
Ipsos has measured the NPD higher than other polling firms since 2017, whereas Léger, Mainstreet and Forum have pulled the NDP's average down during the same period - although none of those skews are overtly dramatic.
We should expect new numbers next week. The 338 district projections will then be updated. Stay tuned.
Philippe J. Fournier is the creator of Qc125 and 338Canada. He teaches physics and astronomy at Cégep de Saint-Laurent in Montreal. For information or media request, please write to info@Qc125.com.
Philippe J. Fournier est le créateur de Qc125 et 338Canada. Il est professeur de physique et d'astronomie au Cégep de Saint-Laurent à Montréal. Pour toute information ou pour une demande d'entrevue médiatique, écrivez à info@Qc125.com.