iiinova — where your digital self keeps evolving

Eh, deleting as I make my collaborators nervous… six years of work should not be undone by me mouthing off on here

000

This is from the same journal that brought us ‘add p-vals to Table 1, and write what you would have done had any been significant’

131

Limited correlation between status and expertise unfortunately!

120

Jack Wilkinson @jdwilko.bsky.social · 11/09/2026

They would also like to see an invalid, non-randomised, per protocol analysis. Medical research so stupid from top to bottom

230

My inbox felt like Vampire Survivors today

011

Jack Wilkinson @jdwilko.bsky.social · 04/09/2026

Absolutely beautiful on the OLED

I didn’t say that all of us should avoid it, but I am happy to do so myself now. Also - I collaborate with many teams across the university, so gain this perspective from that activity.

020

This sounds like you have the worst version of this role possible!

030

Yeah, you’d be (potentially) much better off in a biostats dept?

220

This is the key. Finding good long-term collaborators who do value your expertise. There is a reason I avoid this sort of consultancy as much as possible these days. What kind of setting are you in @phdemetri.bsky.social ?

240

Julia M. Rohrer @dingdingpeng.the100.ci · 31/08/2026

Research is so much more difficult when you care about research integrity. This is why it will never be a priority for most researchers. Researchers benefit from lax standards.

0113

Reposted by Jack Wilkinson

I am once again begging everyone who supervises student theses to stop making students conduct mediation analyses because “a regression isn’t complicated enough for a thesis” 😭

1519723

Jack Wilkinson @jdwilko.bsky.social · 27/08/2026

Absolute headache. We had it good and took it for granted

Jack Wilkinson @jdwilko.bsky.social · 23/08/2026

Someone should make a tool for systematic reviewers to help them assess trustworthiness of eligible studies eh

Jack Wilkinson @jdwilko.bsky.social · 20/08/2026

I guess in the published paper we need to have both the website and instructions to just…email me

100

Reposted by Jack Wilkinson

Ian Hussey @ianhussey.mmmdata.io · 20/08/2026

Could you check if you can see our website without errors/warning and let me know if not? We moved the INSPECT-SR guidance website from inspect.sr to inspect-sr.com because some networks were blocking the somewhat obscure .sr domain. Oddly, I have a report that the latter is throwing warnings too.

inspect-sr.com

INveStigating ProblEmatic Clinical Trials in Systematic Reviews

1072

Jack Wilkinson @jdwilko.bsky.social · 15/08/2026

inspect-sr.com is the home of the INSPECT-SR guidance. Please don’t use INSPECT-SR without it!

inspect-sr.com

INveStigating ProblEmatic Clinical Trials in Systematic Reviews

060

Reposted by Jack Wilkinson

Ian Hussey @ianhussey.mmmdata.io · 14/08/2026

Some firewalls and networks didn't like inspect.sr, so now inspect-sr.com also points to the same site. Thanks to @steamtraen.eu and others for feedback.

inspect-sr.com

INveStigating ProblEmatic Clinical Trials in Systematic Reviews

172

Jack Wilkinson @jdwilko.bsky.social · 13/08/2026

www.graphpad.com/quickcalcs/c...

110

Reposted by Jack Wilkinson

Ian Hussey @ianhussey.mmmdata.io · 13/08/2026

Any suggestions for semi-popular online chi-square calculators? Sometimes less experienced people use them. To validate my {recalc} package, I'm reverse engineering them to make sure the package accommodate their results, as long as they're correct and sane. These are the ones I have already.

* https://www.statscalculators.com/
* https://www.statskingdom.com/
* https://www.omnicalculator.com/statistics
* https://www.statulator.com/
* https://www.danielsoper.com/statcalc/default.aspx
* https://statisticscalculators.com/
* https://statpages.info/
* https://numiqo.com/statistics-calculator/descriptive-statistics
* https://www.standarddeviationcalculator.io/chi-square-calculator
* https://www.socscistatistics.com/tests/chisquare/
* https://www.medcalc.org/en/calc/chisquared-2way.php
* https://www.socscistatistics.com/tests/chisquare2/calculator/
* https://biomath.med.uth.gr/statistics/chi_square.html
* https://www.appinio.com/en/tools/chi-square-calculator

133

Jack Wilkinson @jdwilko.bsky.social · 13/08/2026

There’s a scene in Succession after Tom has been put in charge of Cruises, and he goes to Ken to make him aware of the serious problems at the department. And Ken is like ‘I do not want to know about this. It is your job to make sure I don’t find out.’ A lot of PIs are like this.

1132

Jack Wilkinson @jdwilko.bsky.social · 12/08/2026

Cheers Josef, will have a look

000

Jack Wilkinson @jdwilko.bsky.social · 11/08/2026

We were uploading updates to the INSPECT-SR living guidance to it as a backup to @ianhussey.mmmdata.io ‘s inspect.sr .

inspect.sr

Jack Wilkinson @jdwilko.bsky.social · 11/08/2026

300

Just received the email about OSF no longer hosting projects...yikes. Suggestions for other places to host files and resources for readers?

210

Jack Wilkinson @jdwilko.bsky.social · 04/08/2026

The target trial framework could be really useful for this, if used correctly. Instead it seems to be frequently used to do the opposite ‘we said we emulated a trial…so you can take it our causal claim is justified’

250

Reposted by Jack Wilkinson

Matthew Castle @mrbasilpesto.bsky.social · 27/07/2026

What a shocker. A brilliant writer - he singlehandedly got me hooked on Japanese mystery fiction with Suspect X and was so prolific (even in translation which was only a fraction of his books).

1191

Jack Wilkinson @jdwilko.bsky.social · 22/07/2026

People are certainly trying. @colbyvorland.bsky.social and colleagues are working on INSPECT-AI - software using LLMs to assist with the process

020

Jack Wilkinson @jdwilko.bsky.social · 22/07/2026

In trials we worry about selective outcome reporting... I suspect in much observational research we should be concerned about more or less everything (outcomes, population, exposures!) being selected on the basis of the data.

041

Reposted by Jack Wilkinson

Marion Campbell @marionkcampbell.bsky.social · 16/07/2026

We are hiring!! Our trials unit, CHaRT, is looking to appoint a Deputy Director (Methodology). The role will provide methodological leadership across CHaRT’s portfolio. A really exciting opportunity for anyone interested in a leadership role in clinical trials!! See: www.abdn.ac.uk/jobs/vacanci...

abdn.ac.uk

Deputy Director (Methodology), Medicine, Medical Sciences & Nutrition (ACE014A) | The University of Aberdeen

University of Aberdeen Research Jobs

033

Reposted by Jack Wilkinson

Jamie Cummins @jamiecummins.bsky.social · 14/07/2026

Today we launch the first stable release of RegCheck: v1.0.0. RegCheck makes it easier and quicker to compare study registrations to published papers for consistency - something we know is important in principle, but rarely done in practice. A 🧵 on what's new: regcheck.app

regcheck.app

RegCheck

RegCheck is an AI tool to compare preregistrations with papers instantly.

512883

Jack Wilkinson @jdwilko.bsky.social · 09/07/2026

Waiting until the day of the talk to write the final 1/3 of the talk 😎🚗