Lightnews — Scholar-powered news

Washington Irving @irvingwashington22.bsky.social · 2h

Brought in to help with a project after data collection completed. Assured it would be "quick".

Washington Irving @irvingwashington22.bsky.social · 3h

Oh man—as a kid I didn’t know those SNL commercials were fake. I asked my parents to buy colon blow at the store. Also asked my dad if he had a Wilson trap door at work.

My parents, non-SNL watchers, must have thought I had a head injury

1

Washington Irving @irvingwashington22.bsky.social · 16h

It had been almost a year for me 😬. but for some reason, today was the day!

1

Washington Irving @irvingwashington22.bsky.social · 16h

This sort of insouciance will get you sent straight to the gulag!

1

Washington Irving @irvingwashington22.bsky.social · 22h

i had one of those beautiful moments in life today when you need a source for something--in this case, visualization in bayesian workflow--and i found this aptly titled paper, which is superterrific! 🥰

from bayesian friends including @avehtari.bsky.social

arxiv.org/pdf/1709.01449

arxiv.org

1

Washington Irving @irvingwashington22.bsky.social · 1d

One the unexpected joys and benefits of having been around for a while is no longer being afraid of asking questions. Even if they are perceived as being ‘dumb’ by some people.

Oh, you think my question is stupid? 🤷‍♂️.

2

Washington Irving @irvingwashington22.bsky.social · 1d

Right in the middle of an analysis, with deadline looming, is the perfect time to update my version of R studio, right?

What does this habit say about my psyche?

#rstats

1 6

Washington Irving @irvingwashington22.bsky.social · 1d

Yes—journal prestige is a lousy proxy for quality of reviews. 😩

Washington Irving @irvingwashington22.bsky.social · 1d

Not that I’m a publishing apologist, I’d happily see the whole rotten system vaporized. I think science would be in a better place without such predatory actors.

1

Washington Irving @irvingwashington22.bsky.social · 1d

This latter point is my fear as well. Of course, there is already a mountain of junk/fraud in ‘published’ work. Especially with AI, it’s not practical or possible for humans to read and comment on everything. And then citations creep in and an idea becomes ‘true’…

1

Washington Irving @irvingwashington22.bsky.social · 2d

The stats portion of this contest has officially ended.

Peter Tennant @pwgtennant.bsky.social · 3d

In honor of spooky month, share a 4 word horror story that only someone in your profession would understand:

"Statistical analysis used SPSS"

🏰meg⚔️ @Birthright Audiobook! @impavid.us · 5d

In honor of spooky month, share a 4 word horror story that only someone in your profession would understand

I'll go first: Six page commercial lease.

4

Washington Irving @irvingwashington22.bsky.social · 3d

This is one of those things that is humorous now, but in 10 years when there’s a shortage of actual experts, will be a terrifyingly prescient statement

1

Reposted by Washington Irving

Marcus Helmer 🇺🇸 @bertrandsballot.bsky.social · 4d

I feel like I could run a scared straight program for statistics about what happens when you don't master the basics.

1 5

Washington Irving @irvingwashington22.bsky.social · 4d

And of course the P&T system is so jacked up that it encourages and rewards production of (at times) literal garbage.

1

Washington Irving @irvingwashington22.bsky.social · 4d

I dunno. I think teaching stats is hard because it’s a varied and complex topic.

I think it’s taught poorly cause most clinicians don’t know/don’t care that it’s critical knowledge. And that’s cause the medical training system, as a whole, places little value on this skill.

1 1

Washington Irving @irvingwashington22.bsky.social · 5d

I hit some combination of keys that reloaded some packages and undid some of my data cleaning (eg, scaled vars were gone). This has happened to me a few times before.

Anyone have any thoughts what this is? #rstats

Washington Irving @irvingwashington22.bsky.social · 6d

Without gtsummary and marginaleffects I’d probably have a nervous breakdown.

2

Washington Irving @irvingwashington22.bsky.social · 6d

🔥🔥🔥

Washington Irving @irvingwashington22.bsky.social · 6d

That’s a grey area.

1

Washington Irving @irvingwashington22.bsky.social · 6d

True that!

1 1

Washington Irving @irvingwashington22.bsky.social · 7d

Figure S2 is wild.

1 2

Washington Irving @irvingwashington22.bsky.social · 7d

Too soon.

1

Washington Irving @irvingwashington22.bsky.social · 7d

It’s a bunch of tiny regressions standing on its others shoulders, wearing and oversized trench coat to give the impression of being some kind of large, unconquerable super-being.

2

Washington Irving @irvingwashington22.bsky.social · 7d

Hoo boy, this is good stuff.

Anyone whose work involves health disparities should read this!

Irene Chen @irenetrampoline.bsky.social · Dec 20

tl;dr Healthcare access disparities cascade through the entire ML pipeline.

Check out our working paper here: arxiv.org/pdf/2412.07712

Washington Irving @irvingwashington22.bsky.social · 7d

Regression modeling strategies by @f2harrell.bsky.social is amongst the best out there, imo.

1 6