About EKOS Politics

We launched this website in order to showcase our election research, and our suite of polling technologies including Probit and IVR. We will be updating this site frequently with new polls, analysis and insight into Canadian politics. EKOS's experience, knowledge and sophisticated research designs have contributed positively to many previous elections.

Other EKOS Products

In addition to current political analysis, EKOS also makes available to the public general research of interest, including research in evaluation, general public domain research, as well as a full history of EKOS press releases.

Media Inquires

For media inquires, please contact: Frank Graves President EKOS Research Associates t: 613.235-7215 [email protected]

A Brief Post-Mortem on Election 44

EKOS versus the actual results

[Ottawa – September 21, 2021] After an exciting campaign, the 44th Canadian general election has come to a close. We at EKOS believe we did a very good job in charting the direction of what was one of the tightest and most unpredictable campaigns in recent memory. In the end, we correctly predicted that the Liberals would retain power (we noted that a minority government was the most probable scenario), although we acknowledge that our final estimate of Conservative Party and People’s Party support fell well outside the margin of error.

We are particularly proud of our final seat projection. Not only did we have the overall national seat distribution correct, we accurately predicted 91% of Canada’s 338 electoral districts, which is an extremely strong performance:

LPC

CPC

NDP

BQ

GP

PPC

OTHER

Final projection:

164

113

27

31

3

0

0

Preliminary election results

158

119

25

34

2

0

0

Our main source of error was underestimating the Conservative vote and, by a similar margin, overestimating People’s Party support. Indeed, our total aggregate error (the sum of the absolute values of the differences between each party’s standing in our final poll and their final share of the popular vote) was 12.8. However, if we were to lump the Conservative Party and the People’s Party into a single, small-c conservative category, our aggregate error would fall to just 4.0.

In the coming days, we will be investigating how we missed these two parties by such wide margins. The two hypotheses we will be testing are:

  1. Differential turnout. It is possible that Conservative supporters were simply more likely to show up to the polls, while People’s Party supporters were more likely to stay home. We noted this possibility in our final press release given that People’s Party support is disproportionately focussed among youth, a group that routinely disappoints on Election Day.
  2. Late shifting. It is also possible that large numbers of People’s Party supporters decided to vote Conservative as they reached the ballot booth, either as a last-ditch effort to thwart a Liberal majority or due to aggressive outreach by the Conservative Party in the final days of the campaign. We acknowledged that a late PPC-to-CPC shift was a distinct possibility in our final press release.

Either of these factors – or even a blend of the two factors – could explain why we missed the mark on the two parties. Unfortunately, there was no definitive way to predict either. People’s Party supporters were – by a wide margin – the most enthusiastic about their voting choice and nearly every indicator we tested (likelihood of voting, likelihood of changing one’s mind, etc.) suggested the party’s supporters would hold true to their stated preference. We will also be examining the possibility of methodological errors (such as sampling or measurement errors).

In closing, we would like to thank the 15,172 Canadians who generously responded to our surveys over the 36-day campaign. We would also like to thank those who have provided advice, comments, and feedback throughout the election. Finally, we congratulate all those who participated in the political process and recognize the passion and effort that they bring to Canadian democracy.

Leave a Reply