“We counsel authors to 𝐝𝐢𝐬𝐜𝐨𝐧𝐭𝐢𝐧𝐮𝐞 using 𝐩e𝐫c𝐞n𝐭a𝐠e𝐬 and 𝐬i𝐳e-s𝐩e𝐜i𝐟i𝐜 𝐢n𝐝i𝐜e𝐬 in an attempt to scale data for variation in body size within and among groups. Although 𝗿𝗮𝘁𝗶𝗼𝘀 are simple to form and seemingly simple to interpret, they actually are 𝐞𝐱𝐜𝐞𝐞𝐝𝐢𝐧𝐠𝐥𝐲 𝐝𝐞𝐜𝐞𝐩𝐭𝐢𝐯𝐞 and p𝐨t𝐞n𝐭i𝐚l𝐥y m𝐢s𝐥e𝐚d𝐢n𝐠”

(PDF) The use of percentages and size-specific indices to normalize physiological data for variation in body size: Wasted time, wasted effort?

PDF | Researchers commonly compute percentages or size-specific indices in an attempt to remove effects of body size from physiological data.... | Find, read and cite all the research you need on Rese...

researchgate.net

"If medical schools and universities don't want the literature to be overwhelmed with garbage," Oransky said, "then they should probably stop giving every applicant ... an incentive to publish a lot of crap."

Is AI Flooding Medical Journals With 'Meaningless' Research?

'It's not fraudulent, and it's not really slop,' one expert says

medpagetoday.com

Congrats to @jdwilko.bsky.social and everyone who contributed. www.bmj.com/content/394/...

INSPECT-SR tool for assessing trustworthiness of randomised controlled trials

The integrity of evidence synthesis is threatened by problematic randomised controlled trials, where there are serious concerns about the trustworthiness of the data or findings. Such concerns could b...

bmj.com

The Cochrane Collaboration@cochrane.org · last wk.

INSPECT-SR – a tool for assessing the trustworthiness of randomized controlled trials – has been published today in @bmj.com, giving researchers a structured way to identify problematic studies before they're included in systematic reviews. 🔗 www.cochrane.org/about-us/new... #ResearchIntegrity

Thinking back to the good old days when publishing a paper every three days required some human to be insecure enough to write up two ideas that didn't deserve to see the light of day every single week.

Carl T. Bergstrom@carlbergstrom.com · 3y ago

I fixed the headline. And I honestly don't understand how any journalist could write this story without mentioning the study author's own "extreme productivity".

This model and the computation are a qualitative advance in using diverse data to estimate human growth patterns. Unlike most models, this one is biologically parameterized, not just curve fitting. Is cool.

Catalina I. Fernández, PhD (she/her)@catferna.bsky.social · 2w ago

New in the saga of our causal model of human growth 🚼🧬📈at AJBA: can we reconstruct growth trajectories when kids’ ages are uncertain & all we have is cross-sectional data? Turns out, YES! 🎉 Accurate estimates, with exciting (?!) implications for bioarchaeology and beyond. doi.org/10.1002/ajpa.70358

“These intervals are reasonably narrow, reflecting the quite large sample size. They show, 𝐡𝐨𝐰𝐞𝐯𝐞𝐫, that e𝐯e𝐧 𝐨n t𝐡e m𝐨s𝐭 𝐨p𝐭i𝐦i𝐬t𝐢c i𝐧t𝐞r𝐩r𝐞t𝐚t𝐢o𝐧 there can be 𝐜o𝐧s𝐢d𝐞r𝐚b𝐥e d𝐢s𝐜r𝐞p𝐚n𝐜i𝐞s between the two methods of measurement and we would conclude that 𝐭h𝐞 𝐝e𝐠r𝐞e o𝐟 𝐚g𝐫e𝐞m𝐞n𝐭 was 𝗻𝗼𝘁 𝗮𝗰𝗰𝗲𝗽𝘁𝗮𝗯𝗹𝗲.”

Measuring agreement in method comparison studies - PubMed

Agreement between two methods of clinical measurement can be quantified using the differences between observations made using the two methods on the same subjects. The 95% limits of agreement, estimated by mean difference +/- 1.96 standard deviation of the differences, provide an interval within whi …

pubmed.ncbi.nlm.nih.gov

𝗨𝗹𝘁𝗿𝗮𝘀𝗼𝘂𝗻𝗱 𝗺𝗲𝘁𝗵𝗼𝗱𝘀 𝗮𝗿𝗲 𝗶𝗻𝗮𝗽𝗽𝗿𝗼𝗽𝗿𝗶𝗮𝘁𝗲 𝘁𝗼 𝗮𝘀𝘀𝗲𝘀𝘀 𝘀𝗸𝗲𝗹𝗲𝘁𝗮𝗹 𝗮𝗴𝗲

Ivan Oransky, one of the experts who spoke with ProPublica for this story, said he has encountered other cases where journals failed to retract a study after a university made such a request. “You have a situation where the fox is guarding the henhouse,” he said.

His Research on Pregnant Opioid Users Was Widely Celebrated. Auditors and Experts Found Major Flaws.

Dr. Craig Towers was hailed as a hero for his research on detoxing pregnant opioid users. After he published a study that found naltrexone could help patients stay off drugs, addiction specialists sta...

propublica.org

Imagine if Didier Raoult’s (far more consequential) academic misdemeanours had received any where near the media attention Arday’s did. retractionwatch.com/2024/01/08/j...

Journals retract six Didier Raoult papers for ethics violations

Didier Raoult Two journals of a leading microbiology society have retracted six articles by Didier Raoult after a university investigation found breaches of research ethics in his work.  A sev…

retractionwatch.com

The Simpsons: Stop, He's Already Dead!

ALT: The Simpsons: Stop, He's Already Dead!

static.klipy.com

Charles Piller@charlespiller.bsky.social · 2mo ago

Final word on the collapse of institutional standards in the infamous Didier Raoult case? Great scholarship by @lonnibesancon.bsky.social @elisabethbik.bsky.social and colleagues link.springer.com/article/10.1...

Stop trying to explain what a p-value is in a single sentence (ICYMI) statsepi.substack.com/p/no-you-can...

No, you can't explain what a p-value is with one sentence (Parts I, II)

But I'm going to try and do it in as few as possible. #fml

statsepi.substack.com

“Causal inferential methods require t𝐡e u𝐬e o𝐟 𝐜o𝐮n𝐭e𝐫f𝐚c𝐭u𝐚l𝐬 that are 𝐧𝐨𝐭 𝐢𝐧𝐟𝐨𝐫𝐦𝐞𝐝 𝐛𝐲 𝐚𝐧𝐲 𝐝𝐚𝐭𝐚 (𝗼𝘂𝘁𝘀𝗶𝗱𝗲 𝗼𝗳 𝗰𝗿𝗼𝘀𝘀𝗼𝘃𝗲𝗿 𝘀𝘁𝘂𝗱𝗶𝗲𝘀) and make 𝐚𝐬𝐬𝐮𝐦𝐩𝐭𝐢𝐨𝐧𝐬 that are 𝙪𝒏𝙫𝒆𝙧𝒊𝙛𝒊𝙖𝒃𝙡𝒆, e.g., about the 𝐜o𝐫r𝐞l𝐚t𝐢o𝐧 𝐬t𝐫u𝐜t𝐮r𝐞 𝒐𝙛 𝙥𝒐𝙩𝒆𝙣𝒕𝙞𝒂𝙡 𝙤𝒖𝙩𝒄𝙤𝒎𝙚𝒔.” Excellent read, @f2harrell.bsky.social.

Statistical Models Answer the Fundamental Clinical Question and Provide Clinical Trial Estimands – Statistical Thinking

Specific goals and estimation targets for randomized clinical trials have still not been well defined for general outcome variables. Proponents of causal inference calculus have claimed to define goal...

fharrell.com

Frank Harrell@f2harrell.bsky.social · 2mo ago

New blog article proposing a general statement of the fundamental question a standard RCT should answer and providing robust and powerful statistical methods to answer it: www.fharrell.com/post/rctmod/ #Statistics #StatsSky #EpiSky #clinicaltrial #rct #pharma @stephensenn.bsky.social

“C𝐨u𝐧t𝐞r𝐟a𝐜t𝐮a𝐥-based attempts at ii𝐧d𝐢v𝐢d𝐮a𝐥 𝐩a𝐭i𝐞n𝐭 𝐝e𝐜i𝐬i𝐨n m𝐚k𝐢n𝐠 have led to 𝐧𝐨𝐭𝐡𝐢𝐧𝐠 𝐛𝐮𝐭 𝐜𝐨𝐧𝐟𝐮𝐬𝐢𝐨𝐧” 🔗nice read by @f2harrell.bsky.social: www.fharrell.com/post/rctmod/

Statistical Models Answer the Fundamental Clinical Question and Provide Clinical Trial Estimands – Statistical Thinking

Specific goals and estimation targets for randomized clinical trials have still not been well defined for general outcome variables. Proponents of causal inference calculus have claimed to define goal...

fharrell.com

Does the (live) shingles vaccine protect against dementia? Fergus Hamilton and colleagues provide important evidence in a new preprint using hospital data from the whole of England in a regression discontinuity design from which we *don't* show evidence of a meaningful protective effect /cont

“There are also serious philosophical objections to regarding 𝐩o𝐭e𝐧t𝐢a𝐥 𝐫e𝐬p𝐨n𝐬e𝐬 𝙖𝒔 𝒉𝙖𝒗𝙞𝒏𝙜 𝙧𝒆𝙖𝒍 𝒆𝙭𝒊𝙨𝒕𝙚𝒏𝙘𝒆.” @philipdawid.bsky.social, @stephensenn.bsky.social. 𝐏𝐞𝐫𝐬𝐨𝐧𝐚𝐥𝐢𝐬𝐞𝐝 𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧-𝐌𝐚𝐤𝐢𝐧𝐠 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐂𝐨𝐮𝐧𝐭𝐞𝐫𝐟𝐚𝐜𝐭𝐮𝐚𝐥𝐬. arXiv:2301.11976v2 [stat.ME] 2023. lnkd.in/d2hddCKH

Personalised Decision-Making without Counterfactuals

This article is a response to recent proposals by Pearl and others for a new approach to personalised treatment decisions, in contrast to the traditional one based on statistical decision theory. We a...

arxiv.org

Sobering: initial trials with huge effect, large follow-up trial showing no evidence for an effect. But practice is already locked in and criticism is defused by pointing to random effects meta-analyses which are necessarily dominated by the initial trials. polypharmacy.substack.com/p/we-should-...

We should stop running clinical trials that cannot change practice

The case of prazosin for PTSD nightmares and the PACT trial

polypharmacy.substack.com

“The p𝐨t𝐞n𝐭i𝐚l r𝐞s𝐩o𝐧s𝐞 𝐟r𝐚m𝐞w𝐨r𝐤, introduced by Neyman (1923) and reintroduced and popularised by Rubin (1974), is often taken to be f𝐮n𝐝a𝐦e𝐧t𝐚l t𝐨 𝐭h𝐞 𝐜o𝐧d𝐮c𝐭 𝐨f c𝐚u𝐬a𝐥 𝐢n𝐟e𝐫e𝐧c𝐞. However…” @philipdawid.bsky.social | @stephensenn.bsky.social

Personalised Decision-Making without Counterfactuals

This article is a response to recent proposals by Pearl and others for a new approach to personalised treatment decisions, in contrast to the traditional one based on statistical decision theory. We a...

arxiv.org

Multiverse analysis, abdication of responsibility and manufacturing of doubt: I have written on some downsides I see with multiverse analysis (which I like in principle): arxiv.org/abs/2607.14623 I was inspired/provoked to write it by @dingdingpeng.the100.ci (thanks!)

Preach on it, amen.

Sara Conroy, PhD@episconroy.bsky.social · 3mo ago

I don’t know Dr. Norman, but this seems like a paper motivated by pure annoyance and I love it pubmed.ncbi.nlm.nih.gov/20146096/

“In the case of a 𝗿𝗮𝘁𝗶𝗼 𝗮𝘀 𝗲𝘅𝗽𝗼𝘀𝘂𝗿𝗲, how do we know whether the 𝐜a𝐮s𝐚l e𝐟f𝐞c𝐭 of c𝐡a𝐧g𝐢n𝐠 𝐚 𝐫a𝐭i𝐨 is d𝐮e t𝐨 changing the 𝗻𝘂𝗺𝗲𝗿𝗮𝘁𝗼𝗿, the 𝒅𝙚𝒏𝙤𝒎𝙞𝒏𝙖𝒕𝙤𝒓, or b𝐨t𝐡?

Ratios in regression analyses with causal questions

Ratio measures are often used in medical research. Generally, the reason is to describe a phenomenon with a single number rather than multiple numbers. In

academic.oup.com

Yannick Griep, a former rising star in management research at Radboud University in the Netherlands, is set to lose an undisclosed number of articles from a journal he once edited, Retraction Watch has learned.

Exclusive: Sage to retract multiple articles by dismissed rising star for “compromised” peer-review process

Yannick Griep, a former rising star in management research at Radboud University in the Netherlands, is set to lose an undisclosed number of articles from a journal he once edited, Retraction Watch…

retractionwatch.com

Th resigning editors say the publisher’s decision to become fully open access is “irreconcilable with our vision of science.” According to the journal’s homepage, all submissions from July 1 that end up in the journal will be subject to a $2,990 article processing charge (APC).

‘The exploitation still remains’: Stats journal associate editors resign over $3,000 publishing charge

Eighteen associate editors of the journal Statistics and Computing have announced they will resign after Springer Nature announced the journal would require a fee to publish.  In a July 8 stat…

retractionwatch.com

“If an intervention 𝒊𝒏𝒕𝒆𝒓𝒂𝒄𝒕𝒔 𝒘𝒊𝒕𝒉 participant characteristics, some participants will see larger impacts on their outcome than others.” Higgins, J.P.T. and Li, T. (2022). Exploring Heterogeneity. In Systematic Reviews in Health Research (eds M. Egger, J.P.T. Higgins and G. Davey Smith).

Exploring Heterogeneity

Studies brought together in a meta-analysis are likely to vary in terms of where, when, why, and how they were undertaken. This diversity across the studies often gives rise to heterogeneity: the sta...

onlinelibrary.wiley.com

New preprint: There is only one correct analysis. osf.io/preprints/ps... with @sajedehra.bsky.social and @mntunc.bsky.social We take a critical look at recent proposals for multiverse or many analyst procedures, and strongly argue that epistemic uncertainty should be reduced, not “embraced”. >

Super happy to have contributed to this super important and timely paper, "Using Routinely Collected Data for Research Purposes: Challenges and Mitigation Strategies", led by @sabinehoffmann11.bsky.social and just published in @bmj.com... www.bmj.com/content/393/...

𝗕𝗮𝗰𝗸-𝘁𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻𝘀 𝗶𝗻 𝗿𝗮𝗻𝗱𝗼𝗺-𝗲𝗳𝗳𝗲𝗰𝘁𝘀 𝗺𝗲𝘁𝗮-𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀—𝗜𝗺𝗽𝗮𝗰𝘁 𝗮𝗻𝗱 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝘁𝗶𝗼𝗻. Igelmann JB, Pauly M, @wviechtb.bsky.social. Res Synth Methods. 2026 May 15:1-14. doi: 10.1017/rsm.2026.10096.

𝗚𝗲𝗻𝗲𝗿𝗮𝗹𝗶𝘇𝗲𝗱 𝗔𝗱𝗱𝗶𝘁𝗶𝘃𝗲 𝗠𝗼𝗱𝗲𝗹𝘀. Wood SN. 𝐀𝐧𝐧𝐮𝐚𝐥 𝐑𝐞𝐯𝐢𝐞𝐰 𝐨𝐟 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜𝐬 𝐚𝐧𝐝 𝐈𝐭𝐬 𝐀𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧. 2025;12(Volume 12, 2025):497–526.

Generalized Additive Models

Generalized additive models are generalized linear models in which the linear predictor includes a sum of smooth functions of covariates, where the shape of the functions is to be estimated. They have...

annualreviews.org

Last week, there was widespread indignation at the revelation that some researchers in STEM might not be reading the papers they cite. Here's a recent example of the standard state of affairs in Medicine and Health, published in @bmj.com, one of the world's leading medical journals! 1/5 🧵

Georgia Tomova@georgiatomova.bsky.social · 4mo ago

Tell me you don't understand Bland-Altman limits of agreement without telling me. Authors: "93.5% (100/107) of pairs fell within 95% limits of agreement"

Tell me you don't understand Bland-Altman limits of agreement without telling me. Authors: "93.5% (100/107) of pairs fell within 95% limits of agreement"

“𝐂𝐨𝐫𝐫𝐞𝐥𝐚𝐭𝐢𝐨𝐧 implies specific types of association such as monotone trends or clustering, 𝒃𝙪𝒕 𝒏𝙤𝒕 𝒄𝙖𝒖𝙨𝒂𝙩𝒊𝙤𝒏.” 🔗: moodle2.units.it/pluginfile.p...

Association, correlation and causation - PubMed

Association, correlation and causation

pubmed.ncbi.nlm.nih.gov