Lightnews — Scholar-powered news

Matt Parkes @mattyjparkes.bsky.social · 1d

Maybe they did that so it can’t break the 1st law of thermodynamics. You can’t make or lose energy, it has to stay in constant flux between states

1 4

Matt Parkes @mattyjparkes.bsky.social · 1d

(Not even sure it's a D*A*G, but it's got DAGgy vibes for sure)

2 1

Matt Parkes @mattyjparkes.bsky.social · 1d

(full report: assets.publishing.service.gov.uk/media/5a7ce8...)

assets.publishing.service.gov.uk

1

Matt Parkes @mattyjparkes.bsky.social · 1d

@weratedags.com Saw this one *years* ago, but it's lived in my mind rent-free ever since.

Hi-res: assets.publishing.service.gov.uk/government/u...

5 4 24

Reposted by Matt Parkes

Darren Dahly @statsepi.bsky.social · 3d

Oh good. Finally. Sheesh lads. 😜

Anyway, everyone do pretty please check out @sonrai.bsky.social for all things research data management and stewardship in Ireland (and beyond).

Sonraí - Irish Data Stewardship Network @sonrai.bsky.social · 3d

"Hello World" from Sonraí - the Irish data stewardship network. We aim to promote & support the transition to a FAIR and open research data landscape in Ireland. We will have regular shout-outs and updates on here, and check out our website: www.datastewards.ie

#DataStewards #FAIRdata #OpenResearch

Sonraí – Irish Data Stewardship Network

Irish Data Stewardship Network

www.datastewards.ie

2 3 8

Reposted by Matt Parkes

StatsCI @statsci.bsky.social · 5d

📢 Chelsea&Westminster Hospital NHS Trust Research Dept. are looking for an enthusiastic & dedicated senior statistician with experience working on drug trials to lead on the statistical work for a small portfolio of sponsored studies.
For details please see here: www.chelwest.nhs.uk/about-us/wor...

Work with us

www.chelwest.nhs.uk

2 1

Reposted by Matt Parkes

David Selby @davidselby.bsky.social · 8d

Announcing a new special guest edition in Digital Health! Everything on patient-reported outcomes in mHealth, including algorithmic treatment and measurement allocation, N-of-1 trials, preference learning & handling subjective measurements. 📲

Take a look!

journals.sagepub.com/topic/collec...

1 1

Matt Parkes @mattyjparkes.bsky.social · 8d

Awesome. Always got time for font nerdery. I know our university font and colour guides and try to make all my graphs and slides consistent, which is ridiculously irrelevant time wasting, but oh so satisfying.

2

Reposted by Matt Parkes

UK CTU Network @ukcrc-ctu.org.uk · 9d

Exceptionally pleased to welcome the Michelle Gabriel of the MHRA to the meeting with key updates for delegates around changes to the regulations around clinical trials & recent GCP Inspection findings.

Direct conversations between CTUs & regulators are vital!

#UKCTUNetwork #ClinicalTrialQA2025

1

Reposted by Matt Parkes

LMU Open Science Center @lmu-osc.bsky.social · 10d

Curious about creating a reproducible workflow for your research? 🔍 We provide several self-paced tutorials about tools that make your work more efficient, reproducible, and collaborative.
Self-Paced Tutorial of the Day: Introduction to R 📊 lmu-osc.github.io/introduction...

Welcome – Introduction to R

lmu-osc.github.io

1 17 39

Reposted by Matt Parkes

Paul Naish @paulnaish.bsky.social · 11d

Handling Missingness, Failures, and Non-Convergence in Simulation Studies: A Review of Current Practices and Recommendations

@amstatnews.bsky.social #openaccess www.tandfonline.com/doi/full/10....

Handling Missingness, Failures, and Non-Convergence in Simulation Studies: A Review of Current Practices and Recommendations

Simulation studies are commonly used in methodological research for the empirical evaluation of data analysis methods. They generate artificial datasets under specified mechanisms and compare the p...

www.tandfonline.com

5 6

Reposted by Matt Parkes

UoM Research IT @uomresearchit.bsky.social · 12d

Interested in research data literacy and data skills training? Join the University Library and the @ukdataservice.bsky.social on the 22nd. Lunch is provided!
This event forms part of the Research Data Stewardship community activities - join their Teams space to stay in touch!

Event details (The University of Manchester Library)

The University of Manchester Library

buff.ly

1

Reposted by Matt Parkes

Jack Wilkinson @jdwilko.bsky.social · 15d

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

1 6 5

Matt Parkes @mattyjparkes.bsky.social · 17d

Exactly. True, quality datasets from real phenomena are expensive to obtain, and there are no shortcuts. While the risk that these training datasets get ‘polluted’ with generated stuff gets bigger by the day.

Matt Parkes @mattyjparkes.bsky.social · 17d

(I mean this is also true of any modelling, but it seems like using in silico data means making an order of magnitude more assumptions than usual)

2

Matt Parkes @mattyjparkes.bsky.social · 17d

I think the worrisome bit is that it might be right, but these approximations mean making a whole bunch of untestable assumptions (some explicit, but many implicit), so if you’re wrong, you have no idea why it’s wrong…

1

Matt Parkes @mattyjparkes.bsky.social · 17d

This looks great! The question you should *always* ask if you're thinking about doing an SWT.

Richard Hooper @richardhooper.bsky.social · 17d

I'm doing a webinar in two weeks (15 Oct 1-2pm BST), part of NIHR Research Support Service's Methods Academy series, on the age-old question: should I do a stepped wedge trial?

Free registration, details here: tinyurl.com/z6cjvce3

@nihr-rss.bsky.social @wiphcem.bsky.social @qmul-wiph.bsky.social

2

Reposted by Matt Parkes

Richard Hooper @richardhooper.bsky.social · 17d

I'm doing a webinar in two weeks (15 Oct 1-2pm BST), part of NIHR Research Support Service's Methods Academy series, on the age-old question: should I do a stepped wedge trial?

Free registration, details here: tinyurl.com/z6cjvce3

@nihr-rss.bsky.social @wiphcem.bsky.social @qmul-wiph.bsky.social

1 16 14

Reposted by Matt Parkes

Bennett Institute for Applied Data Science @bennettoxford.bsky.social · 19d

We are hiring researchers!

We’re looking for Epidemiologists / Health Data Scientists to join our growing research team at the Bennett Institute.

Please check out the job advert and tell your friends!

www.bennett.ox.ac.uk/blog/2025/09...

We're hiring researchers to work on OpenSAFELY | Bennett Institute for Applied Data Science

Come and work with us! We’re looking for Epidemiologists / Health Data Scientists to join our growing research team.

www.bennett.ox.ac.uk

4 2

Reposted by Matt Parkes

Darren Dahly @statsepi.bsky.social · 19d

ICYMI:

statsepi.substack.com/p/impact-by-...

Impact by design: The importance of ensuring rigorous research methods right from the start

This was a presentation for Health Research Charities Ireland (September, 2025).

statsepi.substack.com

2 7 23

Reposted by Matt Parkes

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 19d

Some of you monsters will like this: Brutalita Sans - a custom font editor. I recommend a font in which every vowel has a random diacritical mark. As a treat. brutalita.com

Brutalita Sans

Brutalita is an experimental font and font editor, edit in your browser and download OTF.

brutalita.com

3 4 33

Reposted by Matt Parkes

Southampton Clinical Trials Unit @southamptonctu.bsky.social · 22d

What happens when a #ClinicalTrial processes deviate from the approved #protocol? How do we help ensure participate safety is maintained at all times?

A new tool, developed by the @ukcrc-ctu.org.uk network, including the team at SCTU, helps trial teams navigate the process.

Full article below 👇

UK CTU Network @ukcrc-ctu.org.uk · Sep 17

📣 NEW TOOL RELEASED

Trial teams can now better manage #ProtocolDeviations using the #UKCTUNetwork developed Routemap which has been designed to support safer, more compliant research.

Find out more here: ukcrc-ctu.org.uk/deviations-r...

#WorldPatientSafetyDay2025 #ClinicalResearch

1 1

Reposted by Matt Parkes

Our World in Data @ourworldindata.org · 24d

Read more about RCTs and why they’re so important: ourworldindata.org/randomized-c...

Why randomized controlled trials matter and the procedures that strengthen them

Randomized controlled trials are a key tool to study cause and effect. Why do they matter and how do they work?

ourworldindata.org

12 22

Reposted by Matt Parkes

FORM @forumforopen.bsky.social · 24d

New #OpenScience resource alert!📣

Data Management Plans in Open Science: What, Why, & How

Learn why DMPs matter, how they boost transparency & reproducibility, & how to create one for your research

🔗Access the full resource: shorturl.at/nBxtg
#FORM4Open

3 4

Reposted by Matt Parkes

Triad sou. @triadsou.bsky.social · 24d

Biostatisticians Meet AI: Navigating Shifts While Preserving Principles. Bin Zhu. Statistics in Medicine. onlinelibrary.wiley.com/doi/10.1002/...

Biostatisticians Meet AI: Navigating Shifts While Preserving Principles

Click on the article title to read more.

onlinelibrary.wiley.com

1