Georgia Tomova
@georgiatomova.bsky.social
research fellow @clscohorts.bsky.social
epidemiology, causal inference, methods
epidemiology, causal inference, methods
Pinned
Georgia Tomova
@georgiatomova.bsky.social
· Aug 31
First week 'critical' to avoid children missing school later, parents told
Data suggests more than half of children who miss a day at the start of term become persistently absent.
www.bbc.com
A fantastic teaching example of a predictor being misinterpreted as having a causal effect.
#CausalSky #EpiSky
#CausalSky #EpiSky
Reposted by Georgia Tomova
With alt-text:
December 12, 2025 at 3:45 PM
With alt-text:
Is there anything in academia that is not horrifically anticlimactic?
December 12, 2025 at 4:38 PM
Is there anything in academia that is not horrifically anticlimactic?
Reposted by Georgia Tomova
The best example I have of real cross-disciplinary research. I got stucked writting this paper countless times. I just reached the limit of my knowledge repeatedly and could not take it forward. Might have abandoned it altogether without Peter (Epidemiologist) and Melissa's (Lawyer) contributions.
Thrilled to share my latest paper entitled, "Estimating Discrimination in Sentencing: Distinguishing between Good and Bad Controls"
Led by @jpinasanchez.bsky.social, the paper introduces a framework for examining discrimination in criminal justice processes.
🧵 1/10
publicera.kb.se/ejels/articl...
Led by @jpinasanchez.bsky.social, the paper introduces a framework for examining discrimination in criminal justice processes.
🧵 1/10
publicera.kb.se/ejels/articl...
December 8, 2025 at 10:35 AM
The best example I have of real cross-disciplinary research. I got stucked writting this paper countless times. I just reached the limit of my knowledge repeatedly and could not take it forward. Might have abandoned it altogether without Peter (Epidemiologist) and Melissa's (Lawyer) contributions.
Reposted by Georgia Tomova
Thrilled to share my latest paper entitled, "Estimating Discrimination in Sentencing: Distinguishing between Good and Bad Controls"
Led by @jpinasanchez.bsky.social, the paper introduces a framework for examining discrimination in criminal justice processes.
🧵 1/10
publicera.kb.se/ejels/articl...
Led by @jpinasanchez.bsky.social, the paper introduces a framework for examining discrimination in criminal justice processes.
🧵 1/10
publicera.kb.se/ejels/articl...
December 8, 2025 at 10:20 AM
Thrilled to share my latest paper entitled, "Estimating Discrimination in Sentencing: Distinguishing between Good and Bad Controls"
Led by @jpinasanchez.bsky.social, the paper introduces a framework for examining discrimination in criminal justice processes.
🧵 1/10
publicera.kb.se/ejels/articl...
Led by @jpinasanchez.bsky.social, the paper introduces a framework for examining discrimination in criminal justice processes.
🧵 1/10
publicera.kb.se/ejels/articl...
Reposted by Georgia Tomova
New paper alert!
"Public Speakers With Nonnative Accents Garner Less Engagement" -- now out in Psych Science!
This is my first graduate student's first first-author paper (and it was her first-year project).
Short THREAD on the results:
"Public Speakers With Nonnative Accents Garner Less Engagement" -- now out in Psych Science!
This is my first graduate student's first first-author paper (and it was her first-year project).
Short THREAD on the results:
December 4, 2025 at 5:00 PM
New paper alert!
"Public Speakers With Nonnative Accents Garner Less Engagement" -- now out in Psych Science!
This is my first graduate student's first first-author paper (and it was her first-year project).
Short THREAD on the results:
"Public Speakers With Nonnative Accents Garner Less Engagement" -- now out in Psych Science!
This is my first graduate student's first first-author paper (and it was her first-year project).
Short THREAD on the results:
Reposted by Georgia Tomova
December 7, 2025 at 7:09 AM
Reposted by Georgia Tomova
What's a field that convinced itself that causality is out of reach even doing?
(I realize that I'm venturing dangerously close to the positivism discussion we had here in recent days with this post.)
(I realize that I'm venturing dangerously close to the positivism discussion we had here in recent days with this post.)
This is a big recurrent conversation in a field like mine where much of the methodological revision post replication crisis is still ongoing. I think part of this is that we (com folks, but also sociologists and other disciplines borrowing from socpsy) have convinced ourselves that causality is…
December 7, 2025 at 10:51 AM
What's a field that convinced itself that causality is out of reach even doing?
(I realize that I'm venturing dangerously close to the positivism discussion we had here in recent days with this post.)
(I realize that I'm venturing dangerously close to the positivism discussion we had here in recent days with this post.)
Reposted by Georgia Tomova
Made it to Friday, but at what cost?
December 6, 2025 at 12:26 AM
Made it to Friday, but at what cost?
A hidden benefit of having so few papers is I have never published an "association" study.
Hit subscribe for more career advice.
Hit subscribe for more career advice.
December 5, 2025 at 10:35 PM
A hidden benefit of having so few papers is I have never published an "association" study.
Hit subscribe for more career advice.
Hit subscribe for more career advice.
remember when clicking buttons in SPSS was as bad as it could get
Even the the damn twitter card for this Nature Scientific Reports is clearly AI Slop.
December 5, 2025 at 10:21 PM
remember when clicking buttons in SPSS was as bad as it could get
Reposted by Georgia Tomova
For me, the second reason it’s that everything it generates is done so in a way I can’t really interrogate. I just can’t trust it. “Hallucinations” are all it does - it’s just that sometimes they may be accurate. The first reason is the ecological and humans exploitation issues, it’s a tainted tech.
December 4, 2025 at 6:52 PM
For me, the second reason it’s that everything it generates is done so in a way I can’t really interrogate. I just can’t trust it. “Hallucinations” are all it does - it’s just that sometimes they may be accurate. The first reason is the ecological and humans exploitation issues, it’s a tainted tech.
Reposted by Georgia Tomova
Springer-Nature statement
“Whilst the details of peer review are confidential, we can confirm that the article underwent two rounds of review from two independent peer reviewers, supporting an accept decision.”
How am I now expected to believe that two people looked at the paper twice and DGAF?
“Whilst the details of peer review are confidential, we can confirm that the article underwent two rounds of review from two independent peer reviewers, supporting an accept decision.”
How am I now expected to believe that two people looked at the paper twice and DGAF?
Riding the Autism Bicycle to Retraction Town
Does anyone *really* know their Factor Fexcectorn?
nobreakthroughs.substack.com
November 28, 2025 at 1:36 PM
Springer-Nature statement
“Whilst the details of peer review are confidential, we can confirm that the article underwent two rounds of review from two independent peer reviewers, supporting an accept decision.”
How am I now expected to believe that two people looked at the paper twice and DGAF?
“Whilst the details of peer review are confidential, we can confirm that the article underwent two rounds of review from two independent peer reviewers, supporting an accept decision.”
How am I now expected to believe that two people looked at the paper twice and DGAF?
Reposted by Georgia Tomova
Even the the damn twitter card for this Nature Scientific Reports is clearly AI Slop.
November 27, 2025 at 6:56 PM
Even the the damn twitter card for this Nature Scientific Reports is clearly AI Slop.
Reposted by Georgia Tomova
In light of record submission rates and a large volume of AI-generated slop, SocArXiv recently implemented a policy requiring ORCIDs linked in the OSF profile of submitting authors, and narrowing our focus to social science subjects. Today we are taking two more steps:
/1
/1
November 27, 2025 at 2:54 PM
In light of record submission rates and a large volume of AI-generated slop, SocArXiv recently implemented a policy requiring ORCIDs linked in the OSF profile of submitting authors, and narrowing our focus to social science subjects. Today we are taking two more steps:
/1
/1
Reposted by Georgia Tomova
There's no methods development that the observational medical literature can't misuse. Its TTE now, but you look back at when propensity scores were fashionable and see the same thing.
November 28, 2025 at 4:43 PM
There's no methods development that the observational medical literature can't misuse. Its TTE now, but you look back at when propensity scores were fashionable and see the same thing.
Reposted by Georgia Tomova
This year explaining regression to the mean took forever but I’m sure next year will be better.
November 28, 2025 at 10:25 AM
This year explaining regression to the mean took forever but I’m sure next year will be better.
Reposted by Georgia Tomova
Here’s an example of one we did where working through the process made it clear that the data simply weren’t sufficient to answer the question of interest:
onlinelibrary.wiley.com/doi/abs/10.1...
onlinelibrary.wiley.com/doi/abs/10.1...
onlinelibrary.wiley.com
November 27, 2025 at 3:17 PM
Here’s an example of one we did where working through the process made it clear that the data simply weren’t sufficient to answer the question of interest:
onlinelibrary.wiley.com/doi/abs/10.1...
onlinelibrary.wiley.com/doi/abs/10.1...
Reposted by Georgia Tomova
How do I get people to understand that high quality data collected with intention and analyzed by experts have even more potential to revolutionize health care?
Can't even make jokes anymore because Deloitte did use AI to say that AI is good...
www.ctvnews.ca/canada/newfo...
www.ctvnews.ca/canada/newfo...
November 27, 2025 at 7:11 AM
How do I get people to understand that high quality data collected with intention and analyzed by experts have even more potential to revolutionize health care?
Reposted by Georgia Tomova
For some research studies the optimal sample size should be estimated at 0
November 25, 2025 at 10:51 AM
For some research studies the optimal sample size should be estimated at 0
The next seminar of the Causal Inference Interest Group will take place on the 8th December.
More info and registration link: lnkd.in/dky6pduE
More info and registration link: lnkd.in/dky6pduE
November 26, 2025 at 3:39 PM
The next seminar of the Causal Inference Interest Group will take place on the 8th December.
More info and registration link: lnkd.in/dky6pduE
More info and registration link: lnkd.in/dky6pduE
Reposted by Georgia Tomova
HYBRID EVENT: 'Introduction to Quantitative Bias' with Rachel Hughes on Monday 1st December at 10am-12pm UK time.
For those near Leeds, bring your laptop and enjoy this as an in-person session!
Sign-up before 9am on Thursday 27th via: www.eventbrite.co.uk/e/introducti...
For those near Leeds, bring your laptop and enjoy this as an in-person session!
Sign-up before 9am on Thursday 27th via: www.eventbrite.co.uk/e/introducti...
November 24, 2025 at 11:28 AM
HYBRID EVENT: 'Introduction to Quantitative Bias' with Rachel Hughes on Monday 1st December at 10am-12pm UK time.
For those near Leeds, bring your laptop and enjoy this as an in-person session!
Sign-up before 9am on Thursday 27th via: www.eventbrite.co.uk/e/introducti...
For those near Leeds, bring your laptop and enjoy this as an in-person session!
Sign-up before 9am on Thursday 27th via: www.eventbrite.co.uk/e/introducti...
A special day for Cohort Membear from @clscohorts.bsky.social who travelled to Luxembourg to meet its mascot counterpart from @uni.lu ACADI 🧸🦎
Loved talking about causal inference with compositional data to a lovely audience from @liser.lu and LIH.
Many thanks @spilleron.bsky.social & @fnr.lu!
Loved talking about causal inference with compositional data to a lovely audience from @liser.lu and LIH.
Many thanks @spilleron.bsky.social & @fnr.lu!
November 14, 2025 at 1:03 PM
A special day for Cohort Membear from @clscohorts.bsky.social who travelled to Luxembourg to meet its mascot counterpart from @uni.lu ACADI 🧸🦎
Loved talking about causal inference with compositional data to a lovely audience from @liser.lu and LIH.
Many thanks @spilleron.bsky.social & @fnr.lu!
Loved talking about causal inference with compositional data to a lovely audience from @liser.lu and LIH.
Many thanks @spilleron.bsky.social & @fnr.lu!
Reposted by Georgia Tomova
How do we incentivise people to publish fewer papers?
We need to live in a world where saying 'I have published over 500 papers' is widely understood as a red flag, not as something to brag about.
We need to live in a world where saying 'I have published over 500 papers' is widely understood as a red flag, not as something to brag about.
November 12, 2025 at 10:08 AM
How do we incentivise people to publish fewer papers?
We need to live in a world where saying 'I have published over 500 papers' is widely understood as a red flag, not as something to brag about.
We need to live in a world where saying 'I have published over 500 papers' is widely understood as a red flag, not as something to brag about.
Reposted by Georgia Tomova
Thank you for the invitation and for the great discussion!
Recording now available!
November 11, 2025 at 7:53 PM
Thank you for the invitation and for the great discussion!
Recording now available!
November 11, 2025 at 10:02 AM
Recording now available!