top | item 32152053

(no title)

hoodwink | 3 years ago

Hey everyone, this is the follow up post to the experiment posted here on Hacker News a few weeks ago: https://news.ycombinator.com/item?id=31826204.

I'll be hanging out in the replies today if there are any questions I can answer :)

discuss

order

noobhacker|3 years ago

I stalked the post's author (your?) LinkedIn and didn't see any background in statistics. How do you know to design this experiment so nicely?

freemint|3 years ago

It is a pretty standard statistical test taught in any bachelor level class covering statistics (or earlier in Germany we did this in 11 the grade) . This setup also includes https://en.wikipedia.org/wiki/Blocking_(statistics) another pretty standard method you learn by just looking how others do experiments.

Llamamoe|3 years ago

I've said this via Twitter and I'll say it now: I'd expect there to be huge learning effect sizes for anything that alters the way we parse information, even in such "minor" ways as BR.

I'd like to see what the difference would be like after a day, four, and a week of reading articles with BR, if that's viable to enlist people for at all.

noobhacker|3 years ago

Excellent experimental design and analysis!

Is there a way for me to buy you a coffee (or some cash equivalent)? I'd love to incentivize such rigor in online discourse.

An obvious way is to try out readwise ;) but I mostly read online articles and (pirated) books, so I'm not sure I'm a good use case.

hoodwink|3 years ago

these might be the kindest words i've ever gotten in a hacker news thread so thank you! :D

we've actually built an app for reading articles and ebooks (and RSS and PDFs and email newsletters and Twitter threads): https://readwise.io/read

still in private beta but we'll be entering public beta before summer is over!