Martin Posch
@poschm.bsky.social
Medical statistics / Innovative clinical trial designs
Reposted by Martin Posch
#ISCB46 very nice talk by Michael Kammer on COVID-19 prognostic models, which involved a ‘deep dive’ into the pond life of modelling.
Bottom line: “If looking for reliable models, don’t hold your breath.”
Bottom line: “If looking for reliable models, don’t hold your breath.”
August 25, 2025 at 2:25 PM
#ISCB46 very nice talk by Michael Kammer on COVID-19 prognostic models, which involved a ‘deep dive’ into the pond life of modelling.
Bottom line: “If looking for reliable models, don’t hold your breath.”
Bottom line: “If looking for reliable models, don’t hold your breath.”
Reposted by Martin Posch
Pleased to report on two papers on #ANVOVA with @poschm.bsky.social and Franz König
The first lnkd.in/eKmjiQdk
looks at median stratification for a single covariate.
The second lnkd.in/e3DH96G8
considers adjustment for many covariates.
Variance inflation factors are key.
The first lnkd.in/eKmjiQdk
looks at median stratification for a single covariate.
The second lnkd.in/e3DH96G8
considers adjustment for many covariates.
Variance inflation factors are key.
August 12, 2025 at 1:02 PM
Pleased to report on two papers on #ANVOVA with @poschm.bsky.social and Franz König
The first lnkd.in/eKmjiQdk
looks at median stratification for a single covariate.
The second lnkd.in/e3DH96G8
considers adjustment for many covariates.
Variance inflation factors are key.
The first lnkd.in/eKmjiQdk
looks at median stratification for a single covariate.
The second lnkd.in/e3DH96G8
considers adjustment for many covariates.
Variance inflation factors are key.
We invite applications for a 1-year postdoctoral/postgraduate researcher position at the Institute of Medical Statistics, MedUni Vienna working in a collaborative project with regulatory authorities on causal inference for treatment effect estimation in RCTs cloudius.meduniwien.ac.at/index.php/s/...
August 12, 2025 at 12:00 PM
We invite applications for a 1-year postdoctoral/postgraduate researcher position at the Institute of Medical Statistics, MedUni Vienna working in a collaborative project with regulatory authorities on causal inference for treatment effect estimation in RCTs cloudius.meduniwien.ac.at/index.php/s/...
Reposted by Martin Posch
Welcome to the official Bluesky account of SHARE-CTD!
We're a European research network dedicated to enhancing clinical trial data sharing to advance medical research and the betterment of society.
Learn more: share-ctd.eu
#SHARECTD #OpenScience #DataSharing
We're a European research network dedicated to enhancing clinical trial data sharing to advance medical research and the betterment of society.
Learn more: share-ctd.eu
#SHARECTD #OpenScience #DataSharing
NEWS
New article "The validation of prediction models deserves more recognition" published in BMC Medicine
2025.03.24
Begüm Irmak Ön and Ulrich M…
share-ctd.eu
May 2, 2025 at 10:16 AM
Welcome to the official Bluesky account of SHARE-CTD!
We're a European research network dedicated to enhancing clinical trial data sharing to advance medical research and the betterment of society.
Learn more: share-ctd.eu
#SHARECTD #OpenScience #DataSharing
We're a European research network dedicated to enhancing clinical trial data sharing to advance medical research and the betterment of society.
Learn more: share-ctd.eu
#SHARECTD #OpenScience #DataSharing
Reposted by Martin Posch
Congratulations to the #ENAR2025 Student Paper Award Winners! Checkout these eight winners (more to come). Catch their presentations at the 2025 ENAR Spring Conference. #ENAR #StudentAwards #NewOrleans
March 11, 2025 at 2:01 PM
Congratulations to the #ENAR2025 Student Paper Award Winners! Checkout these eight winners (more to come). Catch their presentations at the 2025 ENAR Spring Conference. #ENAR #StudentAwards #NewOrleans
Reposted by Martin Posch
A revised version of the paper with @poschm.bsky.social and Franz Koenig on stratification and covariate adjustment in clinical trials is now up arxiv.org/pdf/2408.06760
We thank Robin Ristl and @timpmorris.bsky.social for helpful comments.
We thank Robin Ristl and @timpmorris.bsky.social for helpful comments.
arxiv.org
March 4, 2025 at 10:49 AM
A revised version of the paper with @poschm.bsky.social and Franz Koenig on stratification and covariate adjustment in clinical trials is now up arxiv.org/pdf/2408.06760
We thank Robin Ristl and @timpmorris.bsky.social for helpful comments.
We thank Robin Ristl and @timpmorris.bsky.social for helpful comments.
Reposted by Martin Posch
This past month has seen the publication of a couple of new helpful papers providing further insights into the thorny issue of #MultipleTesting in trials 1/7
#MethodologyMonday #112
#MethodologyMonday #112
February 24, 2025 at 7:47 AM
This past month has seen the publication of a couple of new helpful papers providing further insights into the thorny issue of #MultipleTesting in trials 1/7
#MethodologyMonday #112
#MethodologyMonday #112
Reposted by Martin Posch
doi.org/10.1002/sim....
Our paper "A Comparison of Statistical Methods for Time-To-Event Analyses in Randomized Controlled Trials Under Non-Proportional Hazards" got published today 🎉
We describe commonly used methods, and compare their performance in a simulation study across different scenarios.
Our paper "A Comparison of Statistical Methods for Time-To-Event Analyses in Randomized Controlled Trials Under Non-Proportional Hazards" got published today 🎉
We describe commonly used methods, and compare their performance in a simulation study across different scenarios.
A Comparison of Statistical Methods for Time‐To‐Event Analyses in Randomized Controlled Trials Under Non‐Proportional Hazards
While well-established methods for time-to-event data are available when the proportional hazards assumption holds, there is no consensus on the best inferential approach under non-proportional hazar...
doi.org
February 20, 2025 at 2:00 PM
doi.org/10.1002/sim....
Our paper "A Comparison of Statistical Methods for Time-To-Event Analyses in Randomized Controlled Trials Under Non-Proportional Hazards" got published today 🎉
We describe commonly used methods, and compare their performance in a simulation study across different scenarios.
Our paper "A Comparison of Statistical Methods for Time-To-Event Analyses in Randomized Controlled Trials Under Non-Proportional Hazards" got published today 🎉
We describe commonly used methods, and compare their performance in a simulation study across different scenarios.
Reposted by Martin Posch
Some news of SHARE-CTD. Good news.
NEWS
First schooling at Wissenschaftszentrum Schloss Reisensburg
2025.02.01
The 1st schooling of the SHARE-CTD project took place in person with internatio…
www.sharectd.eu
February 19, 2025 at 5:07 PM
Some news of SHARE-CTD. Good news.
Reposted by Martin Posch
4 perspectives on the use of LLM in the practice of science www.pnas.org/doi/10.1073/... . Should LLM be seen as collaborators?
How should the advancement of large language models affect the practice of science? | PNAS
Large language models (LLMs) are being increasingly incorporated into scientific workflows.
However, we have yet to fully grasp the implications of...
www.pnas.org
January 28, 2025 at 5:09 AM
4 perspectives on the use of LLM in the practice of science www.pnas.org/doi/10.1073/... . Should LLM be seen as collaborators?
Together with Cyrus Mehta and Ajoy Mukhopadhyay, we present a unified framework for graph-based adaptive designs in multi-arm, multi-endpoint, two-stage studies. This approach integrates multiple strategies to enable flexible confirmatory trial designs. Preprint: arxiv.org/abs/2501.03197
Graph Based, Adaptive, Multi Arm, Multiple Endpoint, Two Stage Design
The graph based approach to multiple testing is an intuitive method that enables a study team to represent clearly, through a directed graph, its priorities for hierarchical testing of multiple hypoth...
arxiv.org
January 11, 2025 at 5:26 PM
Together with Cyrus Mehta and Ajoy Mukhopadhyay, we present a unified framework for graph-based adaptive designs in multi-arm, multi-endpoint, two-stage studies. This approach integrates multiple strategies to enable flexible confirmatory trial designs. Preprint: arxiv.org/abs/2501.03197
Reposted by Martin Posch
A beautifully written interview by Alex Sverdlov featuring my colleague Amy Racine-Poon, published in the International Statistical Review.
doi.org/10.1111/insr...
doi.org/10.1111/insr...
A Conversation With Amy Racine‐Poon
Professor Dr. Amy Racine-Poon is best known for her interdisciplinary contributions as an applied Bayesian statistician in the pharmaceutical industry and healthcare. She was born in Hong Kong and ob...
doi.org
January 9, 2025 at 4:19 PM
A beautifully written interview by Alex Sverdlov featuring my colleague Amy Racine-Poon, published in the International Statistical Review.
doi.org/10.1111/insr...
doi.org/10.1111/insr...
Reposted by Martin Posch
TRIPOD-LLM is out! Check out our consensus guidelines for reporting #LLM research in biomedicine. TRIPOD-LLM is intended to be a living guideline to keep up with the rapid advances in LLMs. Kudos to lead author
Dr. Jack Gallifant
Dr. Jack Gallifant
January 8, 2025 at 8:13 PM
TRIPOD-LLM is out! Check out our consensus guidelines for reporting #LLM research in biomedicine. TRIPOD-LLM is intended to be a living guideline to keep up with the rapid advances in LLMs. Kudos to lead author
Dr. Jack Gallifant
Dr. Jack Gallifant
Reposted by Martin Posch
Priors and decision thresholds in phase 2 and phase 3 randomized controlled trials evaluating drug efficacy using Bayesian methods: a systematic review - @jclinepi.bsky.social www.jclinepi.com/article/S089...
Priors and decision thresholds in phase 2 and phase 3 randomized controlled trials evaluating drug efficacy using Bayesian methods: a systematic review
To describe the priors and decision thresholds in phase 2 and 3 RCTs evaluating drug efficacy using Bayesian methods.
www.jclinepi.com
January 3, 2025 at 11:33 AM
Priors and decision thresholds in phase 2 and phase 3 randomized controlled trials evaluating drug efficacy using Bayesian methods: a systematic review - @jclinepi.bsky.social www.jclinepi.com/article/S089...
Reposted by Martin Posch
"It's easy to get a false positive risk of 40% withOUT any cheating at all"
That's really good. I didn't show enough skepticism about p values when writing in the late 1960. But from a Bayesian point of view, it's easy to get a false positive risk of 40% with any cheating at all (when testing a point null). www.tandfonline.com/doi/full/10....
The False Positive Risk: A Proposal Concerning What to Do About p-Values
It is widely acknowledged that the biomedical literature suffers from a surfeit of false positive results. Part of the reason for this is the persistence of the myth that observation of p < 0.05 is...
www.tandfonline.com
December 27, 2024 at 7:20 PM
"It's easy to get a false positive risk of 40% withOUT any cheating at all"
Reposted by Martin Posch
Amazing collective problem solving in ants:
December 27, 2024 at 5:01 PM
Amazing collective problem solving in ants:
Great essay by David Spiegelhalter!
An essay in Nature discusses how it’s an astonishing achievement that all of statistics and much of science depends on probability considering no one’s sure what it is. 🧪
Why probability probably doesn’t exist (but it is useful to act like it does)
All of statistics and much of science depends on probability — an astonishing achievement, considering no one’s really sure what it is.
go.nature.com
December 21, 2024 at 11:24 PM
Great essay by David Spiegelhalter!
Reposted by Martin Posch
Developing a prediction model?
Ever wondered how to target sample size to improve model fairness and precision of risk estimates?
Check out our new pre-print & software package pmstabilityss
arxiv.org/abs/2407.09293
Ever wondered how to target sample size to improve model fairness and precision of risk estimates?
Check out our new pre-print & software package pmstabilityss
arxiv.org/abs/2407.09293
Sample size for developing a prediction model with a binary outcome: targeting precise individual risk estimates to improve clinical decisions and fairness
When developing a clinical prediction model, the sample size of the development dataset is a key consideration. Small sample sizes lead to greater concerns of overfitting, instability, poor performanc...
arxiv.org
November 6, 2024 at 6:27 PM
Developing a prediction model?
Ever wondered how to target sample size to improve model fairness and precision of risk estimates?
Check out our new pre-print & software package pmstabilityss
arxiv.org/abs/2407.09293
Ever wondered how to target sample size to improve model fairness and precision of risk estimates?
Check out our new pre-print & software package pmstabilityss
arxiv.org/abs/2407.09293
Reposted by Martin Posch
Great to see this R package: stephenrho.github.io/pminternal/
Implements the (in)stability plots and checks recommended by myself & @gscollins.bsky.social after developing a prediction model
Our paper is here: onlinelibrary.wiley.com/doi/full/10....
Implements the (in)stability plots and checks recommended by myself & @gscollins.bsky.social after developing a prediction model
Our paper is here: onlinelibrary.wiley.com/doi/full/10....
Internal Validation of Clinical Prediction Models
Conduct internal validation of a clinical prediction model for a binary outcome.
Produce bias corrected performance metrics (c-statistic, calibration slope) via bootstrap
(simple bootstrap, boots...
stephenrho.github.io
November 19, 2024 at 1:25 PM
Great to see this R package: stephenrho.github.io/pminternal/
Implements the (in)stability plots and checks recommended by myself & @gscollins.bsky.social after developing a prediction model
Our paper is here: onlinelibrary.wiley.com/doi/full/10....
Implements the (in)stability plots and checks recommended by myself & @gscollins.bsky.social after developing a prediction model
Our paper is here: onlinelibrary.wiley.com/doi/full/10....
Reposted by Martin Posch
The Journal of Clinical Epidemiology is, as of today, present at Bluesky 🎉
And, only here, you can have a sneak preview of our new journal and website design.
But of course, our contents remains key, with many thanks to our authors, reviewers, editorial board and editorial team
And, only here, you can have a sneak preview of our new journal and website design.
But of course, our contents remains key, with many thanks to our authors, reviewers, editorial board and editorial team
November 21, 2024 at 6:43 PM
The Journal of Clinical Epidemiology is, as of today, present at Bluesky 🎉
And, only here, you can have a sneak preview of our new journal and website design.
But of course, our contents remains key, with many thanks to our authors, reviewers, editorial board and editorial team
And, only here, you can have a sneak preview of our new journal and website design.
But of course, our contents remains key, with many thanks to our authors, reviewers, editorial board and editorial team
Reposted by Martin Posch
Last year I published research proving (yes, proving 😉 ) that new episodes of Doctor Who on Christmas Day reduce death rates in UK
Since then, the BBC have shown brand new episodes on Christmas Day! Including this year!
Who said my research has no impact? ❤️❤️ #DoctorWho
www.bmj.com/content/383/...
Since then, the BBC have shown brand new episodes on Christmas Day! Including this year!
Who said my research has no impact? ❤️❤️ #DoctorWho
www.bmj.com/content/383/...
November 21, 2024 at 5:33 PM
Last year I published research proving (yes, proving 😉 ) that new episodes of Doctor Who on Christmas Day reduce death rates in UK
Since then, the BBC have shown brand new episodes on Christmas Day! Including this year!
Who said my research has no impact? ❤️❤️ #DoctorWho
www.bmj.com/content/383/...
Since then, the BBC have shown brand new episodes on Christmas Day! Including this year!
Who said my research has no impact? ❤️❤️ #DoctorWho
www.bmj.com/content/383/...
Reposted by Martin Posch
Christmas 2024 Gift no. 4
NEW VIDEO:
"IPD Meta-Analysis: Two-stage or Not Two-Stage?
That is the question..."
youtu.be/WFSAfouhB-8
- guidance for when to choose a one-stage rather than a two-stage approach, & vice versa.
- ideas showcased using real examples (no equations)
I hope useful!
NEW VIDEO:
"IPD Meta-Analysis: Two-stage or Not Two-Stage?
That is the question..."
youtu.be/WFSAfouhB-8
- guidance for when to choose a one-stage rather than a two-stage approach, & vice versa.
- ideas showcased using real examples (no equations)
I hope useful!
IPD Meta-Analysis: Two-stage or Not Two-Stage? That is the question ...
YouTube video by Richard_D_Riley
youtu.be
December 17, 2024 at 9:44 AM
Christmas 2024 Gift no. 4
NEW VIDEO:
"IPD Meta-Analysis: Two-stage or Not Two-Stage?
That is the question..."
youtu.be/WFSAfouhB-8
- guidance for when to choose a one-stage rather than a two-stage approach, & vice versa.
- ideas showcased using real examples (no equations)
I hope useful!
NEW VIDEO:
"IPD Meta-Analysis: Two-stage or Not Two-Stage?
That is the question..."
youtu.be/WFSAfouhB-8
- guidance for when to choose a one-stage rather than a two-stage approach, & vice versa.
- ideas showcased using real examples (no equations)
I hope useful!
Reposted by Martin Posch
If you've been wondering where I went: my team in Oxford (60 of us!) build beautiful tools for NHS data. We help researchers work on the whole nation's GP records while protecting - provably - everyone's privacy. It's big potatoes!
www.youtube.com/watch?v=GRjR...
www.youtube.com/watch?v=GRjR...
OpenSAFELY in a nutshell
YouTube video by Bennett Institute for Applied Data Science
www.youtube.com
November 16, 2024 at 5:20 PM
If you've been wondering where I went: my team in Oxford (60 of us!) build beautiful tools for NHS data. We help researchers work on the whole nation's GP records while protecting - provably - everyone's privacy. It's big potatoes!
www.youtube.com/watch?v=GRjR...
www.youtube.com/watch?v=GRjR...
Reposted by Martin Posch
Hot off the preprint server:
‘Efficiency of nonparametric superiority tests based on restricted mean survival time versus the log-rank test under proportional hazards’
Short thread 👇
1/
arxiv.org/abs/2412.06442
‘Efficiency of nonparametric superiority tests based on restricted mean survival time versus the log-rank test under proportional hazards’
Short thread 👇
1/
arxiv.org/abs/2412.06442
Efficiency of nonparametric superiority tests based on restricted mean survival time versus the log-rank test under proportional hazards
Background: For RCTs with time-to-event endpoints, proportional hazard (PH) models are typically used to estimate treatment effects and logrank tests are commonly used for hypothesis testing. There is...
arxiv.org
December 10, 2024 at 4:49 PM
Hot off the preprint server:
‘Efficiency of nonparametric superiority tests based on restricted mean survival time versus the log-rank test under proportional hazards’
Short thread 👇
1/
arxiv.org/abs/2412.06442
‘Efficiency of nonparametric superiority tests based on restricted mean survival time versus the log-rank test under proportional hazards’
Short thread 👇
1/
arxiv.org/abs/2412.06442