Why QS, PCQ and PQ fluctuate more from survey to survey? | Elections Quebec 2022
Éric Duhaime, Paul St-Pierre Plamondon and Gabriel Nadeau-Dubois during the leaders' debate organized by Radio-Canada, the September 22.
There are sometimes significant discrepancies between the results of polls on the voting intentions of Quebecers, even if they are conducted during the same period. What explains these differences between the results of Mainstreet Research's probes and those of Léger? Explanations.
Claire Durand is a full professor in the Department of Sociology at the University of Montreal and specializes in survey methodology. She claims to have analyzed all the probes carried out by the research firms Mainstreet and Léger on the voting intentions of Quebecers since August 1.
Observation: the Conservative Party of Quebec (PCQ) garners an average of 4% support in the Mainstreet Research polls than in those of Léger.
Conversely, Québec solidaire (QS) averages nearly 4% higher in Leger's projections. The Parti Québécois (PQ) also does slightly better.
Léger and Mainstreet Research are two of the most cited polling firms in the 2022 Quebec elections.
Every time we see a Léger poll, it is possible that it overestimates Québec solidaire. Then, every time you see a Mainstreet poll, it might overestimate the Conservative Party, she says.
Why? The reason for this discrepancy is in the methodology.
Léger conducts its surveys online, while Mainstreet Research uses robocalls.
Generally, but not always, web polls tend to be a little more left-wing. And computerized telephone polls tend to lean a little more to the right, she claims.
An average difference of 4% is not huge, but in a tight race between opponents of the Coalition avenir Québec (CAQ), it can make a difference. It is difficult to establish which method is the most reliable for surveying a population. Some people don't pick up the phone, but answer web surveys, and vice versa.
How do you know who comes closest to reality?
We are waiting for the elections!, answers Claire Durand laughing. We can think that the truth probably lies between the two.
These differences in results do not worry the two firms.
For us in our methodology, it has nothing to do with right or left, says Steve Pinkus, Vice-President of Mainstreet Quebec Research.
According to him, the fact that Mainstreet Research conducts daily soundings gives more credibility to their forecasts.
The other pollsters, they poll maybe once a week. It's a photo. Us is more of a movie. We can trace the evolution of the campaign in real time, he says.
His counterpart at Léger is just as confident.
If we look at the last election campaign, federal, provincial: our polls have always been within the margin of error of the result, believes Christian Bourque, executive vice-president at Léger.
Christian Bourque (archives).
Although he concedes that he is not at x27;free from error, he nevertheless sees with a good eye the coexistence of various types of polls in the Quebec election campaign. The more comparative data we will have between the different methodologies, the better we will understand the situation, he says.
20 or 30 years ago , we said it was the telephone surveys because everyone had the phone at home, everyone answered. Today, that is no longer the case. There is no longer a method that can claim to be the standard from which everything else is necessarily less good.