[ View menu ]
Main

How visualizing inferential uncertainty can mislead readers about treatment effects in scientific results

Filed in Conferences ,Ideas
Subscribe to Decision Science News by Email (one email per week, easy unsubscribe)

STANDARD ERRORS VS STANDARD DEVIATIONS


Click to enlarge

There’s an ancient haiku that goes:

People confuse a
well-estimated mean with
a certain outcome

Ok, that’s not true.

But Jake Hofman, Dan Goldstein, and Jessica Hullman have a new paper (recently accepted at CHI 2020) about this.

They bet you’ll think the results of their paper look are more impressive if you look at the plot on the left pane than if you look at the one on the right.

At least that what the results of their paper say.

Preprint here: http://bit.ly/353kBtj

There’s only a limited number of PDFs available, so grab one today.

Ok, that’s not true either.

Special thanks to @iamwillcai and @_JenAllen for their RAship on this!

0 Comments

No comments

RSS feed Comments

Write Comment

XHTML: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>