Lightnews — Scholar-powered news

Matt Tenan PhD ATC @tenanatc.bsky.social · 1d

Hey @apnews.com, I can fix the headline for you:

"US Carries Out Another Extra-Judicial Execution Killing 6 Unknown People, Trump Says"

4

Reposted by Matt Tenan PhD ATC

Kathleen Bachynski @bachynski.bsky.social · 23d

It was bad enough when politicians were proposing bleach to treat COVID-19. But to actually change the label on acetaminophen?!? “Kennedy said that the F.D.A. would issue a note to doctors about the risk of acetaminophen during pregnancy and begin the process to make a safety change on the label.”

Update from Christina Jewett

www.nytimes.com

1 7 17

Reposted by Matt Tenan PhD ATC

Noah Greifer @noahgreifer.bsky.social · 28d

References for the above, since these papers are not well known, but should be:

King et al (2017): doi.org/10.1111/ajps...
Huling & Mak (2024): doi.org/10.1515/jci-...
Cho et al (2013): doi.org/10.1111/stan...

1 1 4

Matt Tenan PhD ATC @tenanatc.bsky.social · Aug 17

My pain point, the RStan viewer doesn't work 😥😥😥

Lucy D’Agostino McGowan @lucystats.bsky.social · Aug 16

I’ve been dipping my toe into using Positron for #rstats (have been using for everything else for 9 months or so and do love it!) and the biggest pain point is the limit on what I can run in the console - like even fairly tiny shiny apps require source() 😫 is this something I can fix?

2

Matt Tenan PhD ATC @tenanatc.bsky.social · Aug 10

a baby is being held by a woman with a caption that says i just a baby

ALT: a baby is being held by a woman with a caption that says i just a baby

media.tenor.com

1

Matt Tenan PhD ATC @tenanatc.bsky.social · Aug 4

It's a legitimate way to measure metabolism. It has higher error than actual direct or indirect calorimetry, but it's "fine" at scale.

Haven't read the rest of paper yet...

2

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 30

ChatGPT is far better at being my personal mixologist than writing R stats code. #statsky #episky

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 25

Still debating if this is worth a full blog post with reproducible code. Let me know if you'd read it and find it useful...

1 4

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 25

"Central Limit Theorem tells us that we only need to use Gaussian Models!"

Um, Maybe? I guess if you have infinite data and/or don't care about inference at all.

Those of us that want to efficiently detect differences with constrained data need to though... #statsky

1 1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 23

1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 23

I have a 6 and 8 year old. English irritates them to no end because of things like this.

1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 23

I think you mean compromize.

2 3

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 16

I had someone ask recently if I did a sensitivity analysis recently and literally had to ask "sensitive to what?" If you want a sensitivity analysis to every analytical decision I make, you're in for a long presentation!

1 8

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 13

Science is NOT self-correcting.

The arc of the moral universe does NOT bend toward justice.

The second Law of Thermodynamics states that an isolated system will only either increase randomness or stay the same, not become more orderly.

It requires us to put in energy to see defined change.

6

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 9

#statsky #episky

6 18

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 8

Please post when there is a preprint or something citable! I have a paper currently under review where it may be helpful.

I love me a tensor spline interaction.

2

Matt Tenan PhD ATC @tenanatc.bsky.social · Jul 4

Proud to be an American...?

3

Reposted by Matt Tenan PhD ATC

JAMES HEATHERS @jamesheathers.bsky.social · Jun 27

This is quite correct in the most important sense. I'll tell you a story: over ten years ago, I built an automatic p-hacker (in Matlab, I'm old).

It took some data, changed more or less every analysis parameter possible, used every outlier management schema, etc. and then subgroups.

It could...

Dr. Soup @www.duck-rabbit-soup.com · Jun 27

I like this, but I think p hacking can and sometimes does rise to the level of fraud, especially 10 years into the replication crisis.

1 5 17

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 25

Should transgender athletes compete with cisgender athletes in sport? I don't know.

There are more Opinions, Position Stands, & Reviews than Original Research. The Original Research out there, is HIGHLY confounded, full of garbage, and invalid statistical analyses.

2

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 24

This was discussed elsewhere, I think it's a philosophical difference.

I'd argue the other way around, how would you know what outcome is meaningful if you don't understand the system? You don't design a drug without a planned cellular target.

1 1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 24

Haha, I've heard the purpose of data science is to confirm choices the C-suite have already made...

1 1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 24

It's just hard to toe the line between using words normal people understand and being totally wrong in describing what's going on.

1 1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 24

😂 It's the C-suite, the last step is always implied.

But yeah, I think my boss just wants something for a PPT saying "look! The magic has a process you understand!" because the actual analysis plan requires a PhD in statistics and lots post doc learning to get.

1 1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 24

They requested a figure. I think part of the idea is just to show that we have a process, it takes many steps to do well.

It's accompanied by a 10 page statistical analysis plan they won't likely read or understand if they did.

1 1

Matt Tenan PhD ATC @tenanatc.bsky.social · Jun 24

FEEDBACK REQUESTED! I've been tasked with developing a general flow chart for C-suite stakeholders on the process for planned observational causal inference work. I want the figure to be as correct as possible, fit on a Powerpoint slide, and be written for a layperson.

Thoughts #statsky #episky?

5 4 12