Sara Conroy, PhD
@episconroy.bsky.social
Assistant Professor, Department of Pediatrics NCH/OSU | #episky #statsky | @OSUpublichealth and @nationwidekids: Ohio Perinatal Research Network, Center for Perinatal Research | 3 kids | she/her
Pinned
What stage of grief is “inability to talk about it due to rage followed by a feeling of guilt because the importance of these things needs to be communicated”?
Asking for a friend.
Asking for a friend.
Reposted by Sara Conroy, PhD
🎆🎆Welcome to the edge-of-your-seat Semifinals for the 2025 Headline of the Year contest! 🎆🎆
The top 4 seeds have survived to the semis, with the #2 seed surviving two tough battles so far. Will Pretty Obvious hold off Leaked Memo? Will Resolved and Unresolved send the Police Scrambling?
The draw:
The top 4 seeds have survived to the semis, with the #2 seed surviving two tough battles so far. Will Pretty Obvious hold off Leaked Memo? Will Resolved and Unresolved send the Police Scrambling?
The draw:
December 30, 2025 at 12:09 AM
🎆🎆Welcome to the edge-of-your-seat Semifinals for the 2025 Headline of the Year contest! 🎆🎆
The top 4 seeds have survived to the semis, with the #2 seed surviving two tough battles so far. Will Pretty Obvious hold off Leaked Memo? Will Resolved and Unresolved send the Police Scrambling?
The draw:
The top 4 seeds have survived to the semis, with the #2 seed surviving two tough battles so far. Will Pretty Obvious hold off Leaked Memo? Will Resolved and Unresolved send the Police Scrambling?
The draw:
Reviewing poorly written manuscripts is tough. my fist draft review is unfiltered thoughts, good and bad. Then I go back a day or two later to clean it up. Went back to a recent first draft review and I wrote:
“Methods: What!?”
Guess I have a bit more than just clean up for this one. 🫣
“Methods: What!?”
Guess I have a bit more than just clean up for this one. 🫣
December 29, 2025 at 5:20 PM
Reviewing poorly written manuscripts is tough. my fist draft review is unfiltered thoughts, good and bad. Then I go back a day or two later to clean it up. Went back to a recent first draft review and I wrote:
“Methods: What!?”
Guess I have a bit more than just clean up for this one. 🫣
“Methods: What!?”
Guess I have a bit more than just clean up for this one. 🫣
Reposted by Sara Conroy, PhD
Under what circumstances is it acceptable to just not reply to requests to review from journals I've never heard of that are furthermore outside my field?
#AcademicSky
#AcademicSky
December 28, 2025 at 3:21 AM
Under what circumstances is it acceptable to just not reply to requests to review from journals I've never heard of that are furthermore outside my field?
#AcademicSky
#AcademicSky
Reposted by Sara Conroy, PhD
This message hits hard.
December 27, 2025 at 8:38 PM
This message hits hard.
Reposted by Sara Conroy, PhD
The authors quote from an article I wrote in 2023, refuting false claims about government jawboning of social media platforms. One of the claims I directly push back against is the persistent lie that the FBI demanded Twitter censor online speech.
knightcolumbia.org/blog/getting...
knightcolumbia.org/blog/getting...
Getting the Facts Straight: Some Observations on the Fifth Circuit Ruling in Missouri v. Biden
knightcolumbia.org
December 24, 2025 at 7:00 PM
The authors quote from an article I wrote in 2023, refuting false claims about government jawboning of social media platforms. One of the claims I directly push back against is the persistent lie that the FBI demanded Twitter censor online speech.
knightcolumbia.org/blog/getting...
knightcolumbia.org/blog/getting...
I know we asked for authors to include the DAG… but I don’t think throwing a bunch of variables in daggity then copying that image to a supplemental figure and referencing it in the methods section is meeting the spirit of that request 😵💫
December 26, 2025 at 1:10 PM
I know we asked for authors to include the DAG… but I don’t think throwing a bunch of variables in daggity then copying that image to a supplemental figure and referencing it in the methods section is meeting the spirit of that request 😵💫
Reposted by Sara Conroy, PhD
Suppose you ask #AI for improvements to your writing.
The #LLM was trained on, but doesn’t mention, Smith’s work.
You adopt the suggestions containing Smith’s ideas.
You don’t even realize YOU’VE PLAGIARIZED because you’ve never read or heard of Smith.
The #LLM was trained on, but doesn’t mention, Smith’s work.
You adopt the suggestions containing Smith’s ideas.
You don’t even realize YOU’VE PLAGIARIZED because you’ve never read or heard of Smith.
LLM use in scholarly writing poses a provenance problem
Nature Machine Intelligence - LLM use in scholarly writing poses a provenance problem
doi.org
December 23, 2025 at 12:07 PM
Reposted by Sara Conroy, PhD
Fifteen of those twenty years were spent writing unsuccessful grant applications.
You can tell that LotR was written by an academic because Gandalf disappears for like 20 years doing research to answer a single question.
December 26, 2025 at 10:48 AM
Fifteen of those twenty years were spent writing unsuccessful grant applications.
Reposted by Sara Conroy, PhD
Bad-faith actors have used a well-worn playbook to undermine public health interventions and institutions to advance their commercial, political, and personal interests. We need to be careful not to conflate "meeting people where they are" with ceding scientific ground to these actors and agendas.
December 23, 2025 at 9:40 PM
Bad-faith actors have used a well-worn playbook to undermine public health interventions and institutions to advance their commercial, political, and personal interests. We need to be careful not to conflate "meeting people where they are" with ceding scientific ground to these actors and agendas.
Reposted by Sara Conroy, PhD
are you disgruntled by the current safety evaluation landscape? curious about what conceptual clarity, methodological soundness and rigour in AI evaluation might look like? if so, consider coming to dublin and doing a phd with me
apply here: aial.ie/hiring/phd-a...
apply here: aial.ie/hiring/phd-a...
December 22, 2025 at 5:02 PM
Reposted by Sara Conroy, PhD
Many of you have told us you want to support TNG but aren’t always sure how — or where each option lives. So we pulled everything together to make giving easier and clearer. 🧡
You’ll find DAF info, employer matching, and one-time or recurring donations right on our secure Campaign Giving Page:
You’ll find DAF info, employer matching, and one-time or recurring donations right on our secure Campaign Giving Page:
Together, We Keep Trusted Health Information Within Reach
We’re stepping into our biggest year-end effort yet — a $30,000 goal to keep trusted health messengers within reach for everyone in 2026. Your support today helps us start strong.
givebutter.com
December 22, 2025 at 11:58 AM
Many of you have told us you want to support TNG but aren’t always sure how — or where each option lives. So we pulled everything together to make giving easier and clearer. 🧡
You’ll find DAF info, employer matching, and one-time or recurring donations right on our secure Campaign Giving Page:
You’ll find DAF info, employer matching, and one-time or recurring donations right on our secure Campaign Giving Page:
Reposted by Sara Conroy, PhD
Differences like these, in how people answer the same question when using different modes of measurement, are called "mode effects".
Look out for a new introduction to mode effects - with DAGs - coming soon, led by @georgiatomova.bsky.social
Look out for a new introduction to mode effects - with DAGs - coming soon, led by @georgiatomova.bsky.social
People who take phone surveys report that their wellbeing is significantly higher than those who are surveyed online.
What do you think drives this result?
What do you think drives this result?
December 22, 2025 at 2:13 PM
Differences like these, in how people answer the same question when using different modes of measurement, are called "mode effects".
Look out for a new introduction to mode effects - with DAGs - coming soon, led by @georgiatomova.bsky.social
Look out for a new introduction to mode effects - with DAGs - coming soon, led by @georgiatomova.bsky.social
Reposted by Sara Conroy, PhD
MAGA Boomer: At your age in 1970 I paid off college & bought a house w/hard work
Millennials: In 1970 college was 5% of median salary—Now it’s 44%. A median home was $24K—Now its $417K. The top marginal tax rate was 70%—Now its 37%. Sure maybe you did work hard—but then closed the door behind you.
Millennials: In 1970 college was 5% of median salary—Now it’s 44%. A median home was $24K—Now its $417K. The top marginal tax rate was 70%—Now its 37%. Sure maybe you did work hard—but then closed the door behind you.
December 21, 2025 at 2:41 AM
MAGA Boomer: At your age in 1970 I paid off college & bought a house w/hard work
Millennials: In 1970 college was 5% of median salary—Now it’s 44%. A median home was $24K—Now its $417K. The top marginal tax rate was 70%—Now its 37%. Sure maybe you did work hard—but then closed the door behind you.
Millennials: In 1970 college was 5% of median salary—Now it’s 44%. A median home was $24K—Now its $417K. The top marginal tax rate was 70%—Now its 37%. Sure maybe you did work hard—but then closed the door behind you.
Reposted by Sara Conroy, PhD
Manuscript and grant reviewers in biomedical sciences: Do you have any major pet peeves when it comes to formatting of papers or grants that you're reviewing? Anything else not format-related? I'm putting together some recommendations for trainees in our #epidemiology program. Thanks!
December 15, 2025 at 4:52 PM
Manuscript and grant reviewers in biomedical sciences: Do you have any major pet peeves when it comes to formatting of papers or grants that you're reviewing? Anything else not format-related? I'm putting together some recommendations for trainees in our #epidemiology program. Thanks!
Reposted by Sara Conroy, PhD
Anyway, I really feel like the whole environment, including the state of the published literature, is really colluding against students learning how to do proper research. That’s a shame; I always have the impression our students really do want to learn how to do things the right way.
December 20, 2025 at 6:28 PM
Anyway, I really feel like the whole environment, including the state of the published literature, is really colluding against students learning how to do proper research. That’s a shame; I always have the impression our students really do want to learn how to do things the right way.
Reposted by Sara Conroy, PhD
It's important to extend yourself the grace to accept that you made the best decisions that you could with the information you had at the time.
December 20, 2025 at 3:04 AM
It's important to extend yourself the grace to accept that you made the best decisions that you could with the information you had at the time.
Reposted by Sara Conroy, PhD
I’ve spent the past two days as pediatric ward attending and frankly we need both more and even better vaccines not fewer
December 20, 2025 at 12:10 AM
I’ve spent the past two days as pediatric ward attending and frankly we need both more and even better vaccines not fewer
Reposted by Sara Conroy, PhD
I keep wanting to say something, and I keep not knowing what to say.
The trans community does not harm cis people by existing. They are just trying to live their lives, same as anyone else. That life doesn't look exactly like mine; my life doesn't match anyone else's. That's okay.
The trans community does not harm cis people by existing. They are just trying to live their lives, same as anyone else. That life doesn't look exactly like mine; my life doesn't match anyone else's. That's okay.
December 19, 2025 at 10:57 PM
I keep wanting to say something, and I keep not knowing what to say.
The trans community does not harm cis people by existing. They are just trying to live their lives, same as anyone else. That life doesn't look exactly like mine; my life doesn't match anyone else's. That's okay.
The trans community does not harm cis people by existing. They are just trying to live their lives, same as anyone else. That life doesn't look exactly like mine; my life doesn't match anyone else's. That's okay.
Reposted by Sara Conroy, PhD
They want us to not want to be professors:
So our students don't question their propaganda.
So our research doesn't challenge their lies.
So our institutions can be replaced with so-called AI.
So our students don't question their propaganda.
So our research doesn't challenge their lies.
So our institutions can be replaced with so-called AI.
December 19, 2025 at 11:42 PM
They want us to not want to be professors:
So our students don't question their propaganda.
So our research doesn't challenge their lies.
So our institutions can be replaced with so-called AI.
So our students don't question their propaganda.
So our research doesn't challenge their lies.
So our institutions can be replaced with so-called AI.
Reposted by Sara Conroy, PhD
When I'm feeling particularly hopeless about the future of professoring as a profession, I try to remind myself: That's what they want. They want us to not want to be professors anymore.
December 19, 2025 at 8:57 PM
When I'm feeling particularly hopeless about the future of professoring as a profession, I try to remind myself: That's what they want. They want us to not want to be professors anymore.
Reposted by Sara Conroy, PhD
A great opportunity for folks interested in data science + AI; lots going on at Hopkins in this area! Spread the word and apply!
Join us in advancing data science and AI research! The Johns Hopkins Data Science and AI Institute Postdoctoral Fellowship Program is now accepting applications for the 2026–2027 academic year. Apply now! Deadline: Jan 23, 2026. Details and apply: apply.interfolio.com/179059
December 19, 2025 at 2:20 PM
A great opportunity for folks interested in data science + AI; lots going on at Hopkins in this area! Spread the word and apply!
Reposted by Sara Conroy, PhD
ICYMI: "Clinical prediction models using machine learning in oncology: challenges and recommendations"
--> bmjoncology.bmj.com/content/4/1/...
#machinelearning #digitalhealth #predictionmodels #methodsmatter
--> bmjoncology.bmj.com/content/4/1/...
#machinelearning #digitalhealth #predictionmodels #methodsmatter
Clinical prediction models using machine learning in oncology: challenges and recommendations
Clinical prediction models are widely developed in the field of oncology, providing individualised risk estimates to aid diagnosis and prognosis. Machine learning methods are increasingly being used t...
bmjoncology.bmj.com
December 19, 2025 at 10:16 AM
ICYMI: "Clinical prediction models using machine learning in oncology: challenges and recommendations"
--> bmjoncology.bmj.com/content/4/1/...
#machinelearning #digitalhealth #predictionmodels #methodsmatter
--> bmjoncology.bmj.com/content/4/1/...
#machinelearning #digitalhealth #predictionmodels #methodsmatter
Reposted by Sara Conroy, PhD
December 18, 2025 at 10:25 AM
Reposted by Sara Conroy, PhD
Just gave my last talk of the year!
2025 was quite packed, I gave talks about:
- the age-period-cohort problem
- making rigorous causal inference more mainstream
- mediation analysis
- marginaleffects
- causal graphs (x10)
If you're curious, check out my slides here: juliarohrer.com/resources/
2025 was quite packed, I gave talks about:
- the age-period-cohort problem
- making rigorous causal inference more mainstream
- mediation analysis
- marginaleffects
- causal graphs (x10)
If you're curious, check out my slides here: juliarohrer.com/resources/
Resources
Here you can find a collection of things that may be helpful, including slide decks, a curated list of introductory papers and blog posts, as well as some infographics I have generated to explain v…
juliarohrer.com
December 18, 2025 at 12:38 PM
Just gave my last talk of the year!
2025 was quite packed, I gave talks about:
- the age-period-cohort problem
- making rigorous causal inference more mainstream
- mediation analysis
- marginaleffects
- causal graphs (x10)
If you're curious, check out my slides here: juliarohrer.com/resources/
2025 was quite packed, I gave talks about:
- the age-period-cohort problem
- making rigorous causal inference more mainstream
- mediation analysis
- marginaleffects
- causal graphs (x10)
If you're curious, check out my slides here: juliarohrer.com/resources/
Reposted by Sara Conroy, PhD
Fun fact: the key term used in these discussions is clinical equipoise. Essentially, for a study to be ethical there must be a genuine uncertainty whether the intervention (withholding the vaccine) or the standard approach (giving the vaccine) is better for patients. This study is 100% unethical.
This is the best piece I’ve read so far on why the Guinea-Bissau RCT, in which a proven life-saving vaccine will be deliberately WITHHELD, is unethical
“When benefit is established, withholding an intervention is no longer neutral experimentation it becomes premeditated harm”
“When benefit is established, withholding an intervention is no longer neutral experimentation it becomes premeditated harm”
The planned hepatitis B birth-dose trial in Guinea-Bissau raises serious ethical concerns. Withholding a proven, life-saving vaccine from newborns to answer speculative questions is an absence of equipoise with real downstream harms for trust in vaccines.
bktitanji.substack.com/p/how-unethi...
bktitanji.substack.com/p/how-unethi...
December 19, 2025 at 12:57 AM
Fun fact: the key term used in these discussions is clinical equipoise. Essentially, for a study to be ethical there must be a genuine uncertainty whether the intervention (withholding the vaccine) or the standard approach (giving the vaccine) is better for patients. This study is 100% unethical.