Jack Wilkinson
@jdwilko.bsky.social
Centre for Biostatistics, Uni of Manchester. INSPECT-SR, a tool to identify problematic clinical trials. Research misconduct, fertility research. Own opinions.
Pinned
Jack Wilkinson
@jdwilko.bsky.social
· Sep 5
INSPECT-SR: a tool for assessing trustworthiness of randomised controlled trials
The integrity of evidence synthesis is threatened by problematic randomised controlled trials (RCTs). These are RCTs where there are serious concerns about the trustworthiness of the data or findings....
www.medrxiv.org
www.medrxiv.org/content/10.1...
INSPECT-SR: A tool for assessing trustworthiness of randomised controlled trials.
INSPECT-SR: A tool for assessing trustworthiness of randomised controlled trials.
I set up my Sega Saturn every year at Christmas. Whether or not I can get it working determines whether or not Christmas is ruined. Hard branching paths. Wish me luck.
December 22, 2025 at 12:05 PM
I set up my Sega Saturn every year at Christmas. Whether or not I can get it working determines whether or not Christmas is ruined. Hard branching paths. Wish me luck.
I cannot be trusted to attend a meeting without a calendar invite
December 19, 2025 at 11:04 AM
I cannot be trusted to attend a meeting without a calendar invite
Reposted by Jack Wilkinson
Have you got a PhD in Statistics (or related field) and experience in Statistical Consulting? A continuing position at the Australian National University is now open 🇦🇺🦘🐨.
Would love to get an #rstats person if possible ☺️
Apply by 18 Jan 👉 jobs.anu.edu.au/jobs/course-... #statssky #statsky
Would love to get an #rstats person if possible ☺️
Apply by 18 Jan 👉 jobs.anu.edu.au/jobs/course-... #statssky #statsky
Course Coordinator - Canberra / ACT, ACT, Australia
Classification: Academic Level BSalary package: $121,598 – 137,870 per annum plus 17% superannuation Terms: Full-time, Continuing (flexible arrangements, job share, or part time hours will be consider...
jobs.anu.edu.au
December 19, 2025 at 4:08 AM
Have you got a PhD in Statistics (or related field) and experience in Statistical Consulting? A continuing position at the Australian National University is now open 🇦🇺🦘🐨.
Would love to get an #rstats person if possible ☺️
Apply by 18 Jan 👉 jobs.anu.edu.au/jobs/course-... #statssky #statsky
Would love to get an #rstats person if possible ☺️
Apply by 18 Jan 👉 jobs.anu.edu.au/jobs/course-... #statssky #statsky
Reposted by Jack Wilkinson
Out today in @annalsofim.bsky.social
doi.org/10.7326/ANNA...
Our systematic review of 11 RCTs found bisphosphonates may reduce short-term pain but increase risk for AEs. Results limited by substantial, unexplained heterogeneity, introduced by inclusion of terminated trial data.
doi.org/10.7326/ANNA...
Our systematic review of 11 RCTs found bisphosphonates may reduce short-term pain but increase risk for AEs. Results limited by substantial, unexplained heterogeneity, introduced by inclusion of terminated trial data.
Efficacy and Safety of Bisphosphonates for Complex Regional Pain Syndrome: A Systematic Review and Meta-analysis: Annals of Internal Medicine: Vol 0, No 0
Background: Clinical guidelines recommend bisphosphonates for complex regional pain syndrome (CRPS) despite limited evidence of efficacy. Purpose: To determine the efficacy and safety of bisphosphonat...
doi.org
December 16, 2025 at 6:56 AM
Out today in @annalsofim.bsky.social
doi.org/10.7326/ANNA...
Our systematic review of 11 RCTs found bisphosphonates may reduce short-term pain but increase risk for AEs. Results limited by substantial, unexplained heterogeneity, introduced by inclusion of terminated trial data.
doi.org/10.7326/ANNA...
Our systematic review of 11 RCTs found bisphosphonates may reduce short-term pain but increase risk for AEs. Results limited by substantial, unexplained heterogeneity, introduced by inclusion of terminated trial data.
Reposted by Jack Wilkinson
You might be interested in the scrutiny R package
lhdjung.github.io/scrutiny/ind...
and the associated webapp
errors.shinyapps.io/scrutiny/
lhdjung.github.io/scrutiny/ind...
and the associated webapp
errors.shinyapps.io/scrutiny/
Error detection in science
Test published summary statistics for consistency and reconstruct some of the processes which created them. The package aims to make these methods easy to use in a tidyverse-friendly way, helping the ...
lhdjung.github.io
December 10, 2025 at 8:16 AM
You might be interested in the scrutiny R package
lhdjung.github.io/scrutiny/ind...
and the associated webapp
errors.shinyapps.io/scrutiny/
lhdjung.github.io/scrutiny/ind...
and the associated webapp
errors.shinyapps.io/scrutiny/
Reposted by Jack Wilkinson
We might be at a stage where systematic reviews without checks of trustworthiness become a problem in itself - even a danger to patients, as these reviews are considered as highest level of evidence and the foundation of guidelines and clinical practice
Currently busy with updating a systematic review and have the impression that the flood of "clinical studies" from certain countries is intensifying - results too good to be true: enduring effects (usually uncommon), no drop-out, perfectly balanced sample sizes etc.
December 3, 2025 at 8:35 PM
We might be at a stage where systematic reviews without checks of trustworthiness become a problem in itself - even a danger to patients, as these reviews are considered as highest level of evidence and the foundation of guidelines and clinical practice
Reposted by Jack Wilkinson
Superb and enlightening, if quite disturbing webinar. The recording is now up on the @chemistryworld.com YouTube channel.
www.youtube.com/watch?v=wWj5...
www.youtube.com/watch?v=wWj5...
Restoring integrity: tackling fraud and data manipulation in scientific research
YouTube video by Chemistry World
www.youtube.com
November 28, 2025 at 9:20 PM
Superb and enlightening, if quite disturbing webinar. The recording is now up on the @chemistryworld.com YouTube channel.
www.youtube.com/watch?v=wWj5...
www.youtube.com/watch?v=wWj5...
Reposted by Jack Wilkinson
#rstats
It is with profound sadness I heard that my long-time friend and colleague, John Fox passed away this week.
He was the author of {car}, {effects}, {Rcmdr}, ... and numerous influential books. I will miss him greatly.
www.john-fox.ca
It is with profound sadness I heard that my long-time friend and colleague, John Fox passed away this week.
He was the author of {car}, {effects}, {Rcmdr}, ... and numerous influential books. I will miss him greatly.
www.john-fox.ca
John Fox: Books and Software
www.john-fox.ca
November 28, 2025 at 3:26 PM
#rstats
It is with profound sadness I heard that my long-time friend and colleague, John Fox passed away this week.
He was the author of {car}, {effects}, {Rcmdr}, ... and numerous influential books. I will miss him greatly.
www.john-fox.ca
It is with profound sadness I heard that my long-time friend and colleague, John Fox passed away this week.
He was the author of {car}, {effects}, {Rcmdr}, ... and numerous influential books. I will miss him greatly.
www.john-fox.ca
People are already getting this wrong when using INSPECT-SR. This is going to be biggest headache I think.
Do not try to reproduce p-values from rounded summary statistics. You can (should) check whether they are consistent - you can achieve this by calculating the largest/smallest p-value consistent with the rounded data. Mark Bolland’s app may help: reappraised.shinyapps.io/check_p_vals...
reappraised.shinyapps.io
November 28, 2025 at 11:30 AM
People are already getting this wrong when using INSPECT-SR. This is going to be biggest headache I think.
Free online Intro to INSPECT-SR workshop in January - this one was designed to be convenient for Australian colleagues but may work for others too: www.trybooking.com/uk/FPDL
Introduction to INSPECT-SR Training Workshop Jan (Australia)
An introductory 2-hour online workshop will introduce participants to the INSPECT-SR tool for assessing trustworthiness of randomised controlled...
www.trybooking.com
November 27, 2025 at 4:55 PM
Free online Intro to INSPECT-SR workshop in January - this one was designed to be convenient for Australian colleagues but may work for others too: www.trybooking.com/uk/FPDL
Reposted by Jack Wilkinson
If missed out before, there are more spaces on this training now!
More on INSPECT-SR here: www.cochrane.org/about-us/new...
More on INSPECT-SR here: www.cochrane.org/about-us/new...
November 27, 2025 at 4:21 PM
If missed out before, there are more spaces on this training now!
More on INSPECT-SR here: www.cochrane.org/about-us/new...
More on INSPECT-SR here: www.cochrane.org/about-us/new...
Uh oh - I made a joke about a contentious topic
November 27, 2025 at 4:12 PM
Uh oh - I made a joke about a contentious topic
Do not try to reproduce p-values from rounded summary statistics. You can (should) check whether they are consistent - you can achieve this by calculating the largest/smallest p-value consistent with the rounded data. Mark Bolland’s app may help: reappraised.shinyapps.io/check_p_vals...
reappraised.shinyapps.io
November 27, 2025 at 2:05 PM
Do not try to reproduce p-values from rounded summary statistics. You can (should) check whether they are consistent - you can achieve this by calculating the largest/smallest p-value consistent with the rounded data. Mark Bolland’s app may help: reappraised.shinyapps.io/check_p_vals...
Why does every target trial emulation study have to include a bit that says "this shows how great target trial emulation is. RCTs are non-generalisable and expensive"? Imagine if every RCT said "this shows how great RCTs are. We did not have to rely on strong, untestable assumptions".
November 27, 2025 at 12:05 PM
Why does every target trial emulation study have to include a bit that says "this shows how great target trial emulation is. RCTs are non-generalisable and expensive"? Imagine if every RCT said "this shows how great RCTs are. We did not have to rely on strong, untestable assumptions".
Reposted by Jack Wilkinson
This tendency to confuse credibility of claims with “were the authors doing their best” is strong in psych. Eg defensiveness about Cross Lagged Panel Models despite now knowing they have false positives rates. “But they didn’t know that at the time” doesn’t increase evidential value now.
November 19, 2025 at 1:18 AM
This tendency to confuse credibility of claims with “were the authors doing their best” is strong in psych. Eg defensiveness about Cross Lagged Panel Models despite now knowing they have false positives rates. “But they didn’t know that at the time” doesn’t increase evidential value now.
Never understand the idea that failing to pre-register an RCT before 2010 (say) does not constitute risk of bias. RoB is not about figuring out whether researchers did their best according to the standards of the time. Meta-research suggests that estimates did tend to reduce after intro of reg.
November 19, 2025 at 1:00 AM
Never understand the idea that failing to pre-register an RCT before 2010 (say) does not constitute risk of bias. RoB is not about figuring out whether researchers did their best according to the standards of the time. Meta-research suggests that estimates did tend to reduce after intro of reg.
Reposted by Jack Wilkinson
Our plenary speaker will be Lisa Bero, with 'Commercial influence on research: what, how and why'
We do this work because health decision/policy should be based on evidence. I am particularly interested in the commercial determinants of health.
en.wikipedia.org/wiki/Lisa_Bero
#AIMOS2025
We do this work because health decision/policy should be based on evidence. I am particularly interested in the commercial determinants of health.
en.wikipedia.org/wiki/Lisa_Bero
#AIMOS2025
November 18, 2025 at 11:07 PM
Our plenary speaker will be Lisa Bero, with 'Commercial influence on research: what, how and why'
We do this work because health decision/policy should be based on evidence. I am particularly interested in the commercial determinants of health.
en.wikipedia.org/wiki/Lisa_Bero
#AIMOS2025
We do this work because health decision/policy should be based on evidence. I am particularly interested in the commercial determinants of health.
en.wikipedia.org/wiki/Lisa_Bero
#AIMOS2025
Have increased capacity for this December INSPECT-SR online training workshop following a successful 1st event today. Book here: www.trybooking.com/uk/FKHV
Introduction to INSPECT-SR Training Workshop December
An introductory 2-hour online workshop will introduce participants to the INSPECT-SR tool for assessing trustworthiness of randomised controlled...
www.trybooking.com
November 6, 2025 at 5:55 PM
Have increased capacity for this December INSPECT-SR online training workshop following a successful 1st event today. Book here: www.trybooking.com/uk/FKHV
Reposted by Jack Wilkinson
We've got loads of resources here for people to get started and be convinced to try it: asapbio.org/about/why-pr...
Why Preprints? – ASAPbio
Discover how preprints accelerate scientific discovery, increase visibility of research, and enable rapid feedback while maintaining research quality standards.
asapbio.org
October 25, 2025 at 6:40 PM
We've got loads of resources here for people to get started and be convinced to try it: asapbio.org/about/why-pr...
Reposted by Jack Wilkinson
Happy to follow up individually if there's more info I can provide. See also our FAQs: asapbio.org/about/faq/pr...
Preprint FAQ – ASAPbio
asapbio.org
October 25, 2025 at 6:40 PM
Happy to follow up individually if there's more info I can provide. See also our FAQs: asapbio.org/about/faq/pr...
Reposted by Jack Wilkinson
We have senior people in our department telling PhD students not to post preprints as journals will refuse to publish due to prior publication. Is there anywhere in health this is actually true? Genuine question, but I doubt it?
October 24, 2025 at 1:09 PM
We have senior people in our department telling PhD students not to post preprints as journals will refuse to publish due to prior publication. Is there anywhere in health this is actually true? Genuine question, but I doubt it?
Reposted by Jack Wilkinson
Free online workshop for assessing trustworthiness of RCTs
Introductory online INSPECT-SR workshop. November 6th, 12-2pm UK-time. Free, places limited. BOOK: www.trybooking.com/uk/events/la...
Introduction to INSPECT-SR Training Workshop November
An introductory 2-hour online workshop will introduce participants to the INSPECT-SR tool for assessing trustworthiness of randomised controlled...
www.trybooking.com
October 22, 2025 at 8:16 AM
Free online workshop for assessing trustworthiness of RCTs
I agree with Tim that the value of target trials is to help think about assumptions and limitations (what we would like to do vs what we can do). But I fear it is going to be used differently-to minimise limitations, implying a NRSI is as good as randomised tpmorris.substack.com/p/firing-at-...
Firing at Target
The Target statement recently appeared in JAMA, and I hereby confer it with two acronym-related awards: “Most dubious” and possibly “Longest gap between two successive letters in the acronym”.
tpmorris.substack.com
October 21, 2025 at 3:55 PM
I agree with Tim that the value of target trials is to help think about assumptions and limitations (what we would like to do vs what we can do). But I fear it is going to be used differently-to minimise limitations, implying a NRSI is as good as randomised tpmorris.substack.com/p/firing-at-...
