T's instead of error bars

Get your science fix here: research, quackery, activism and all the rest
Post Reply
User avatar
shpalman
Princess POW
Posts: 7556
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond
Contact:

T's instead of error bars

Post by shpalman » Tue Dec 06, 2022 2:19 pm

having that swing is a necessary but not sufficient condition for it meaning a thing
@shpalman@mastodon.me.uk

IvanV
After Pie
Posts: 1731
Joined: Mon May 17, 2021 11:12 am

Re: T's instead of error bars

Post by IvanV » Tue Dec 06, 2022 2:34 pm

Thank you. I think I have never seen something that comes quite so blatantly and obviously into the category of cargo cult science. I remember first coming across the term on this forum, and having to think carefully about what it might mean. For all my interest in pseudoscience, I had never seen that term before, and presumed the poster must have made it up. I was very impressed when I realised what a nice distinction it was. But it was apparently first used by Richard Feynmann, and deserves to be better known.

monkey
Dorkwood
Posts: 1555
Joined: Wed Nov 13, 2019 5:10 pm

Re: T's instead of error bars

Post by monkey » Tue Dec 06, 2022 3:55 pm

I wanted to do a joke about a t-test, but I read the article and it had already been done.

User avatar
Bird on a Fire
Princess POW
Posts: 10120
Joined: Fri Oct 11, 2019 5:05 pm
Location: Portugal

Re: T's instead of error bars

Post by Bird on a Fire » Tue Dec 06, 2022 11:28 pm

Thoroughly depressing.

Using a bar chart to plot a distribution of data is f.cking stupid. Plot the actual data, or at least a violin or box plot or something.
We have the right to a clean, healthy, sustainable environment.

User avatar
dyqik
Light of Blast
Posts: 6430
Joined: Wed Sep 25, 2019 4:19 pm
Location: A rock in the middle of the Pacific
Contact:

Re: T's instead of error bars

Post by dyqik » Wed Dec 07, 2022 12:01 am

Bird on a Fire wrote:
Tue Dec 06, 2022 11:28 pm
Thoroughly depressing.

Using a bar chart to plot a distribution of data is f.cking stupid. Plot the actual data, or at least a violin or box plot or something.
Violin plots are best, because they display the actual distribution, and inevitably look a bit Georgia O'Keeffe.

User avatar
Bird on a Fire
Princess POW
Posts: 10120
Joined: Fri Oct 11, 2019 5:05 pm
Location: Portugal

Re: T's instead of error bars

Post by Bird on a Fire » Wed Dec 07, 2022 12:13 am

Might start calling them O'Keeffe plots
We have the right to a clean, healthy, sustainable environment.

User avatar
nekomatic
Dorkwood
Posts: 1124
Joined: Mon Nov 11, 2019 3:04 pm

Re: T's instead of error bars

Post by nekomatic » Fri Dec 23, 2022 4:35 pm

Move-a… side, and let the mango through… let the mango through

User avatar
jimbob
Light of Blast
Posts: 4512
Joined: Mon Nov 11, 2019 4:04 pm
Location: High Peak/Manchester

Re: T's instead of error bars

Post by jimbob » Sun Jan 01, 2023 8:02 pm

dyqik wrote:
Wed Dec 07, 2022 12:01 am
Bird on a Fire wrote:
Tue Dec 06, 2022 11:28 pm
Thoroughly depressing.

Using a bar chart to plot a distribution of data is f.cking stupid. Plot the actual data, or at least a violin or box plot or something.
Violin plots are best, because they display the actual distribution, and inevitably look a bit Georgia O'Keeffe.
I tend to prefer normalised probability plots, but yes.

I have converted about half my colleagues to those.
Have you considered stupidity as an explanation

User avatar
Bird on a Fire
Princess POW
Posts: 10120
Joined: Fri Oct 11, 2019 5:05 pm
Location: Portugal

Re: T's instead of error bars

Post by Bird on a Fire » Mon Jan 02, 2023 12:20 pm

There is an R package for everything, now including correctly fitting Ts as error bars, via the wonderfully named geom_terrorbar() function:

https://mival.netlify.app/blog/2023/01/ ... terrorbar/
We have the right to a clean, healthy, sustainable environment.

Post Reply