this post was submitted on 17 Jan 2025
13 points (100.0% liked)

Canada

7330 readers
420 users here now

What's going on Canada?



Related Communities


🍁 Meta


🗺️ Provinces / Territories


🏙️ Cities / Local Communities

Sorted alphabetically by city name.


🏒 SportsHockey

Football (NFL): incomplete

Football (CFL): incomplete

Baseball

Basketball

Soccer


💻 Schools / Universities

Sorted by province, then by total full-time enrolment.


💵 Finance, Shopping, Sales


🗣️ Politics


🍁 Social / Culture


Rules

  1. Keep the original title when submitting an article. You can put your own commentary in the body of the post or in the comment section.

Reminder that the rules for lemmy.ca also apply here. See the sidebar on the homepage: lemmy.ca


founded 4 years ago
MODERATORS
 

The Liberal Party has seen a remarkable turnaround in its fortunes in recent weeks. Following Chrystia Freeland’s resignation a month ago, the Conservative lead had reached an all-time high of 25 points. In our latest polling, however, that advantage has narrowed to just 11 points, with the Conservatives leading 39 points to 28. At 17 points, the NDP is in third place, and their declared intention to bring down the government does not appear to have produced any benefits.

you are viewing a single comment's thread
view the rest of the comments
[–] wise_pancake@lemmy.ca 3 points 13 hours ago* (last edited 13 hours ago)

Can I just take a minute to vent about this data viz

They have used a spline like a hobby spline and not a smoothing spline on that chart. It is a major pet peeve of mine when people use these curves to "interpolate" and make data look prettier. If you are interpolating points on a chart you need to choose a curve that actually fits through all the points, and is smooth.

There are points on this chart where the data inverts by over 90° and goes backwards, so you have more than one y point on the same x axis. You can't tell where the data points are and these curves absolutely cannot represent voting sentiment. A scatter plot, or regular line plot would have worked perfectly fine, but instead EKOS who should be good with data has created these mangled to fuck charts...

Another downfall of these types of curves is they can create bends where no data is, which means they tell a story that has zero basis in reality, but it makes the first derivative smooth. That same effect can create curves which extend outside of the data range, but that's not an issue on this particular chart.