In full transparency

Dear readers,

I have updated to website to show the contrast between the final 338Canada projection and the actual election results. By browsing through the website, you will notice that the correct winner was identified in 299 of 338 districts (88,4%). Among the remaining 39, the correct winner was within the margin of error (moe) 27 times.

Twelve districts were complete misses (wrong winner outside moe).

In the following weeks, I will study those districts that were wrong and work to improve the model.

The graphs of individual districts are static images and look like this:

The couloured bars are the confidence intervals and the black dots, the election results for each party.

You will see some pretty awesome projections, such as Barrie–Springwater–Oro-Medonte (Ontario):

Or Hamilton-Mountain (Ontario):

Or Saskatoon-University (Saskatchewan):

But you will also come across some misses, like Central Nova (Nova Scotia):

Ouch. Or Montmagny–L'Islet–Kamouraska–Rivière-du-Loup (Quebec):

Or Elmwood-Transcona (Manitoba):

The goal here is transparency.

Some readers online will surely mock my misses, and I guess I have to live with it. But I believe most readers will see it for what it is: a statistical ensemble of 338 districts. Naturally, there were going to be some misses - "hyperlocal effects" are not easy to decipher during a campaign where I have to pay attention to all 338.

But 88,4% (299/338) correctly identified winners?

Only 12 (12/338 = 3,6%) wrong winners outside the margin of error?

That's not bad at all.

You can find your districts here:

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

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