Advantage Liberal: What advanced modelling tells us about why the Liberals are winning
April 11, 2025
With just two weeks left in the campaign, the data suggests Mark Carney and the Liberal Party are within striking distance of defying expectations if just a few months ago and pulling off a fourth straight election win. While many observers had written off the Liberals, new analysis offers a more nuanced picture—one that highlights the opportunity ahead for Carney, if he can consolidate his strengths and overcome a an electorate anxious about the uncertainty created by Donald Trump and still reeling from the affordability crisis that gripped the nation for the past two years.
We recently ran a binary logistic regression model to better understand what’s driving support for the Liberals in this election. In plain terms, a logistic regression is a way of identifying which factors increase or decrease the likelihood that someone will vote Liberal. It’s a method that lets us separate the signal from the noise—to distinguish which perceptions and personal characteristics really matter in predicting vote choice.
Rather than just looking at who says they’ll vote Liberal, we isolate the variables most associated with that decision and evaluate their strength, while controlling for everything else. It’s like trying to understand what ingredients make a voter more likely to pick Carney’s name on the ballot—economic views, issue priorities, education, gender, and personal impressions all get thrown into the mix. The model helps us see which ones matter most.
What did we find?
It’s the Economy, and Carney
The most consistent and powerful predictor of a Liberal vote is a sense that Mark Carney is the better choice to manage the economy and deal with Donald Trump. Among all the variables we tested—from education to gender to impressions of Pierre Poilievre—Carney’s perceived strength on economic management was the standout.
Voters who believe Carney is better equipped to grow the economy, deal with Trump, and even help manage the cost of living are significantly more likely to support the Liberals. That tells us something critical about the current campaign landscape: people are still very open to economic leadership, and Carney’s background in global finance and economics is an incredibly powerful asset.
It’s also worth noting that Carney’s perceived competence extends beyond the economy. Voters who see him as stronger on climate change and housing are also more inclined to support him. But economic credibility and dealing with Trump remain the foundation.
Likeability—and the Personal Brand—Matters
Another powerful predictor is how people feel about Mark Carney himself. Those with a positive impression of him are far more likely to vote Liberal. In fact, this was one of the strongest effects in the model. In an election shaped by a growing precarity mindset and a general sourness about the state of the country, personal impressions can make or break a candidate.
What this tells us is that the Liberals don’t just have a policy pitch—they have a messenger who, when seen in a favourable light, can dramatically improve their chances. For someone that barely 10% could recognize when he announced his candidacy to lead the Liberals, Carney is now a definite asset for the Liberals. Where he is known and is liked, support is solid.
Interestingly, having a negative view of Pierre Poilievre also pushes some voters toward the Liberals, but not nearly as powerfully. This isn’t shaping up to be a “stop Poilievre” campaign in the way past elections were framed around “stopping Harper.” The Liberal vote, at least for now, appears more driven by pro-Carney sentiment than anti-Conservative sentiment.
A Party Still Tied to Its Past
But it’s not all smooth sailing for the Liberals. One of the strongest negative predictors of a Liberal vote is a sense that the country is headed in the wrong direction. Those who feel Canada is on the wrong track are far less likely to vote Liberal, regardless of what they think about Carney.
This is a crucial insight. Even though Justin Trudeau is no longer Prime Minister, the weight of his government’s legacy still hangs over the Liberal brand. Voters’ dissatisfaction with the status quo remains a major barrier.
In this context, Carney’s challenge is clear: he’s had to convince voters that a vote for him is not a vote for more of the same. And so far, he’s done that sufficiently.
Education Helps, Demographics Less So
Support for the Liberals is also more likely among those with a university education. That fits with long-standing trends, particularly in urban and suburban ridings where progressive, university-educated voters have traditionally supported the Liberals in past elections. However, gender, age, and even indicators of precarity had limited influence on vote intention in the model – all else being equal.
That doesn’t mean these demographic groups aren’t important. It simply means they don’t independently predict a Liberal vote as strongly as issue-based perceptions or personal impressions of the leaders. Campaigns that rely solely on micro-targeting by age or gender might miss the bigger picture: people are choosing based on who they trust to manage the economy, guide the country through this unprecedent moment, and fix the problems they care most about.
So What Happens Next?
With two weeks left in the campaign, Carney and the Liberals have the advantage and are posed to win, despite several factors working against them.
On one hand, the electorate is deeply unhappy. Most Canadians believe the country is on the wrong track, and that’s a tough environment for any incumbent party—even with a new leader. But on the other hand, Carney has something rare: a profile that signals competence, a sense that he’s different from Trudeau, and the ability to speak credibly about the issues people care about most—Trump, cost of living, housing, and the economy.
The data shows that the Liberals aren’t winning today because people feel nostalgic for Trudeau-era policies or because they deeply dislike Poilievre. They’re winning because people believe Mark Carney might be the right person to get Canada back on course and defend it from the threats posed by Donald Trump. This statistical model clearly validates that.
That’s the story of this campaign. And if Carney can make that story clearer to more voters in the next two weeks, he can lock down the victory.
The Model at Work
Here’s how the model works in practice by simulating five different voter profiles. Each scenario tweaks a few perceptions to show how various beliefs influence the probability of someone voting Liberal.
When a person holds all favourable views—thinking Carney is the best on the economy and dealing with Trump, has a positive impression of Carney, a negative view of Poilievre, and believes the country is on the right track—the model predicts a 73% probability of voting Liberal. This is the “ideal” Liberal voter as imagined in the model. However, if we hold everything constant but remove the positive impression of Carney, the probability drops to 41%, showing just how critical Carney’s personal brand is to the party’s chances.
Things get even more precarious when someone does like Carney but also believes the country is off on the wrong track. Even with positive perceptions elsewhere, the probability falls to 56%. This underscores a key vulnerability: dissatisfaction with the direction of the country still weighs heavily on Liberal chances—even when Carney is otherwise well-regarded.
Now imagine a voter who thinks Carney is only strong on the economy but doesn’t hold a negative view of Poilievre, isn’t impressed with his ability to deal with Trump, and believes the country is off track. Their probability of voting Liberal drops sharply to just 23%.
Finally, when none of these positive traits are present, the odds bottom out at 2%.
These scenarios demonstrate how perceptions of leadership, competence on key issues, and the mood of the country work together—and how pivotal it is for the Liberals to connect on all three fronts
Methodology
The survey was conducted with 1,900 adult Canadians over the age of 18 from April 3 to 8, 2025. A random sample of panelists were invited to complete the survey from a set of partner panels based on the Lucid exchange platform. These partners are typically double opt-in survey panels, blended to manage out potential skews in the data from a single source.
The margin of error for a comparable probability-based random sample of the same size is +/- 2.1%, 19 times out of 20.
The data were weighted according to census data to ensure that the sample matched Canada’s population according to age, gender, educational attainment, and region. Totals may not add up to 100 due to rounding.
This survey was paid for by Abacus Data Inc.
Abacus Data follows the CRIC Public Opinion Research Standards and Disclosure Requirements that can be found here: https://canadianresearchinsightscouncil.ca/standards/
Binary Logistic Regression
To identify the key predictors of support for the Liberal Party under Mark Carney’s leadership, we used a binary logistic regression model. This statistical technique estimates the likelihood that a respondent chooses a particular outcome—in this case, voting Liberal—based on a set of independent variables.
Unlike linear regression, which predicts a continuous outcome, logistic regression is used when the dependent variable is binary (e.g., support vs. no support). The model calculates the probability that an individual will vote Liberal, based on factors such as personal impressions of the leaders, issue priorities, demographic characteristics, and views on the state of the country.
The coefficients from the model represent the change in the log-odds of voting Liberal associated with each predictor, holding all other variables constant. A positive coefficient indicates an increased likelihood of voting Liberal, while a negative coefficient suggests a decreased likelihood.
This method allows us to isolate the individual impact of each factor and identify which attributes are most strongly associated with support for the Liberals—offering a more precise understanding of what’s driving voter behaviour in the current election context.
While traditional R-squared (as used in linear regression) doesn’t directly apply to logistic regression, we use pseudo R-squared measures to assess model fit.
- Nagelkerke’s R-squared (0.5932) is an adjusted version of the Cox & Snell R-squared, scaled to range between 0 and 1. It suggests that the model explains approximately 59% of the variation in vote intention—indicating strong explanatory power for a social science model.
- McFadden’s rho-squared (0.5811) is another commonly used pseudo R-squared that compares the fit of the full model against a null (intercept-only) model. Values above 0.4 are typically considered indicative of a very good model fit.
Both values suggest this logistic model provides a robust and meaningful explanation for what drives someone to vote Liberal in this election scenario.
ABOUT ABACUS DATA
We are Canada’s most sought-after, influential, and impactful polling and market research firm. We are hired by many of North America’s most respected and influential brands and organizations.
We use the latest technology, sound science, and deep experience to generate top-flight research-based advice to our clients. We offer global research capacity with a strong focus on customer service, attention to detail, and exceptional value.
And we are growing throughout all parts of Canada and the United States and have capacity for new clients who want high quality research insights with enlightened hospitality.
Our record speaks for itself: we were one of the most accurate pollsters conducting research during the 2021 Canadian election following up on our outstanding record in the 2019, 2015, and 2011 federal elections.
Contact us with any questions.
Find out more about how we can help your organization by downloading our corporate profile and service offering.
