Lightnews — Scholar-powered news

Daniel P. Moriarity

@dpmoriarity.bsky.social

5.1K followers 1.9K following 2.9K posts

Assistant Professor of Clinical Psychology @ UPenn | Quant-curious | Lv. 11 Dwarf paladin Inflammatory phenotyping, physiometrics, precision psychiatry Statistics, Transparency, + Rigor Editor @ Psychological Science

Posts Media Videos Starter Packs

Pinned

Daniel P. Moriarity @dpmoriarity.bsky.social · Jun 28

First paper from my lab @upenn.edu (open access) @ Biological Psychiatry w/ @emilyrperkins.bsky.social [email protected]

We discuss the need to falsify theories of biology predicting syndromes vs. syndromes in ways that allow both to be true 🧵1/10

authors.elsevier.com/sd/article/S...

3 9 63

Daniel P. Moriarity @dpmoriarity.bsky.social · 11h

of course, thanks for helping me dig through!

Daniel P. Moriarity @dpmoriarity.bsky.social · 12h

you for your help!

FWIW (still some digging to do), I think it has something to do w/ consecutive assessments per person. I thought specifying ID but per bsky.app/profile/mans... was enough but when I specify start + end time the curve the "at risk" corrects to be N (right) instead of obvs (left)

1 2

Reposted by Daniel P. Moriarity

Russ Poldrack @russpoldrack.org · 1d

OpenNeuro @openneuro.bsky.social just hit a huge milestone: 1500 datasets! Congrats to the team on making this project so successful over the last 7 years.

2 29 140

Reposted by Daniel P. Moriarity

Don Lynam @drlynam.bsky.social · 17h

Exciting news from the Academy of Psychological Clinical Science--a joint effort to enhance open science training in clinical psychology!

If you are interested, you can the papers mentioned in the email here:
Van Til et al. osf.io/h34jg/files/...
OSC paper (Lynam et al.) osf.io/preprints/ps...

1 7 14

Reposted by Daniel P. Moriarity

Jeremy Berg @jeremymberg.bsky.social · 14h

VOTE VOTE VOTE VOTE VOTE

If you have an election in your area, VOTE!

Ballot receipt email from Allegheny County

2 7 23

Daniel P. Moriarity @dpmoriarity.bsky.social · 15h

interesting, thank you so much! If my following of the documentation is correct, does this automatically transition this to an interval censored scheme, or is right censoring still the right fit?

I think (?) right censored is most appropriate. RQ is on time-to-remission in treatment

Daniel P. Moriarity @dpmoriarity.bsky.social · 15h

thanks, Libby! Sorry for misunderstanding, incorrectly assumed that the graph was to identify the 50% threshold of whether the event happened

Pulled up the figure and it never crosses .5, which odd. Seems that it isn't determining median relating to # of people, its using # of observations...

Daniel P. Moriarity @dpmoriarity.bsky.social · 18h

eh, as I'm digging in a bit more I don't think interval censoring is feasible since the assessments are still day of vs "did the event happen between now and your last assessment"

Daniel P. Moriarity @dpmoriarity.bsky.social · 18h

I double checked the coding and came up with some observations that underscored I think I'm misunderstanding something fundamental. Also had the thought that maybe interval censoring is more appropriate here since we only do assessments every ~2 weeks bsky.app/profile/dpmo...

Daniel P. Moriarity @dpmoriarity.bsky.social · 18h

I do have consecutive time periods for each individual, but I'm seeing two things during some diagnostics that are making me thing I misunderstood how to structure my data or communicate to the command what the data structure is 1/3

Daniel P. Moriarity @dpmoriarity.bsky.social · 18h

Since this is right-censored, my understanding was that time points before the event should be 0, the event should be 1, then observations after the event should be missing but, when I run just the surv(), it is labeling the "0"s as censored yellow highlights = same ID across pics) 2/2

Daniel P. Moriarity @dpmoriarity.bsky.social · 18h

Daniel P. Moriarity @dpmoriarity.bsky.social · 19h

Thanks, Frank! Im trying to focus on the median here, it seems from the N and Events columns that this should have reached the 50% threshold, unless I'm misunderstanding something (probably am at this point)

1 1

Reposted by Daniel P. Moriarity

Shannon Pileggi @pipinghotdata.com · 19h

R-Ladies Philly 🔔 is delighted to welcome ✨ Alex Velez✨ on Tuesday, Oct 28 for a lunch & learn discussion on "From data to story"! Hope you can join us 🤗 #rstats #rladies 💜 www.meetup.com/rladies-phil...

Lunch & Learn with Alex Velez: From data to story, Tue, Oct 28, 2025, 12:00 PM | Meetup

The typical graph in a business communication often leaves our audience confused and overwhelmed. In this session, you’ll be walked through an illustration of how to avoid

www.meetup.com

1 2 7

Daniel P. Moriarity @dpmoriarity.bsky.social · 20h

good point, attached for more info, thanks! All time points after the event are missing, event =1, pre-event =0.

Going to check into the logical coding when I get back to the computer...that might be the lead!

Daniel P. Moriarity @dpmoriarity.bsky.social · 20h

I didn't think so? But maybe I set up the coding wrong. There are multiple observations per individual, but any time point prior to the event is labeled as "0" and when the event happens they are labeled as "1", but I'm gathering from your response this set-up is incorrect...

Daniel P. Moriarity @dpmoriarity.bsky.social · 20h

Thank you, Stephen!

Daniel P. Moriarity @dpmoriarity.bsky.social · 20h

Correct, it's a Cox regression from using survfit(surv()) but no covariates in this model. And only 1 event per person!

Daniel P. Moriarity @dpmoriarity.bsky.social · 21h

I interpreted this to mean if the event happened on > 50% of the sample , which it did. Or are you referring to some other property?

Daniel P. Moriarity @dpmoriarity.bsky.social · 1d

That would have been good info to include...

Survival package, survfit function

Daniel P. Moriarity @dpmoriarity.bsky.social · 1d

Cannot for the life of me find a relevant post on CrossValidated so internet please help.

Running a survival analysis where >50% of the sample had the event, but it isn't able to calculate the median or confidence interval. Never seen this one before... Any explanations?

#Rstats

4 2 3

Reposted by Daniel P. Moriarity

Matthew Cortland (they) @matthewcort.land · 2d

If you're looking for a Democrat running for federal office who both gets it and gets how to effectively talk about it?

Check out @jamestalarico.bsky.social

www.tiktok.com/t/ZTMUVyMoL/

Theocracy is the most dangerous form of government.

TikTok video by James Talarico

www.tiktok.com

11 40

Reposted by Daniel P. Moriarity

Olivia Guest · Ολίβια Γκεστ @olivia.science · 11d

New preprint 🌟 Psychology is core to cognitive science, and so it is vital we preserve it from harmful frames. @irisvanrooij.bsky.social & I use our psych and computer science expertise to analyse and craft:

Critical Artificial Intelligence Literacy for Psychologists. doi.org/10.31234/osf...

🧵 1/

Cover page of Guest, O., & van Rooij, I. (2025, October 4). Critical Artificial Intelligence Literacy for Psychologists. https://doi.org/10.31234/osf.io/dkrgj_v1

Table 1 Guest, O., & van Rooij, I. (2025, October 4). Critical Artificial Intelligence Literacy for Psychologists. https://doi.org/10.31234/osf.io/dkrgj_v1

Table 2 Guest, O., & van Rooij, I. (2025, October 4). Critical Artificial Intelligence Literacy for Psychologists. https://doi.org/10.31234/osf.io/dkrgj_v1

9 110 290

Reposted by Daniel P. Moriarity

Rich Raho @richraho.bsky.social · 3d

Chicago priest Fr. Larry Dowling describes procession to ICE facility: “No one had the courage to speak directly to us. No one from Homeland Security could stand in the presence of the Monstrance holding the Blessed Sacrament. No wonder. Evil is repelled, recoils in the presence of Christ.”

290 5K 16K

Reposted by Daniel P. Moriarity

Mark Histed @markhisted.org · 3d

Seeing a lot of celebration of this as a win.

But at NIH we have seen this exact play before.

It looks like it is the Vought strategy -and to stop the lawless firings we have to see the bigger picture.
A 🧵:

Trump Administration Will Rehire Scores of Experts Fired in Error

www.nytimes.com

14 330 790

Reposted by Daniel P. Moriarity

Mark Histed @markhisted.org · 3d

Looks from here like the goal is to create confusion, and focus public attention on a subset of the most outrageous firings — to distract from the other firings.

We shouldn’t be fooled, and should demand that all the illegal shutdown RIFs are made null and void. /end

3 78 320