Very important work 👇👇👇

'It is ironic that when faced with a dichotomous outcome, standard statistical procedures, such as logistic regression or probit analysis, attempt to reconstruct a continuous ‘protomeasurement’ which is presumed to give rise to the dichotomous values.' senns.uk/SIDD.html

classic

Differential Treatment Effects of Subgroup Analyses in Phase 3 Oncology Trials From 2004 to 2020. Sherry, Hahn, McCaw, Jaoude, Kouzy, Lin, Minsky, Fuller, ToMeirson, Msaouel, Ludmir. JAMA Netw Open.jamanetwork.com/journals/jaman…

Same Old Challenges in Subgroup Analysis—Should We Do More About Methods Implementation? Stefan Schandelmaier, Gordon Guyatt. JAMA Netw Open. jamanetwork.com/journals/jaman…

I love doing methodology work but it is so hard to get it funded!😭😭

To help researchers find the right methodology to follow, we are currently establishing the Library of Guidance for Health Scientists (LIGHTS)

When analysing qualitative data, you will encounter several methodological approaches; however, if your main aim is to create a theory or something from scratch, an abductive approach could be a solution. But what’s an abductive analysis?

Estimands can be used in studies of healthcare interventions to clarify the interpretation of treatment effects.

This article illustrates how to use the estimands framework by applying it to an ongoing trial Brennan Kahan
bmj.com/content/384/bm…

New reporting guideline (the accordstatement) now out in PLOS Medicine for reporting clinical recommendations or research using consensus methodology.

--> tinyurl.com/53ndzafm

#transparency #reportingguidelines

Minimal important differences crucial to interpret patient-reported outcomes. Anchor based & statistical approaches used. Recent study: no consistent relation between standard deviations & anchor based MIDs. Use of statistical approach should cease now! doi.org/10.1016/j.jcli…

Confidence distributions are distributional summaries of evidence. They’re like Bayesian posteriors but without prior distribution assumptions. I wrote a tutorial paper in Statistics in Medicine for clinical trial statisticians AusTriM NHMRC CTC
onlinelibrary.wiley.com/doi/10.1002/si…

Precision Medicine: Too Big to Fail?

Excellent read; the money spent on this would be much better spent on prevention, screening, surgery, radiation

sites.tufts.edu/insight/2016/1…

Why Stating Hypotheses in Grant Applications Is Unnecessary JAMA Miguel Hernán Sander Greenland jamanetwork.com/journals/jama/…

jclinepi.com/article/S0895-…

Exciting findings from our latest Meta-Science study in prognostic biomarkers in kidney transplantation just published @JASN ! We've appraised 800+ biomarker studies. Let's dive into the details. 📚 #Biomarkers Paris Transplant Group Alexandre Loupy journals.lww.com/jasn/abstract/…
👇

If more scientists calculated confidence distributions, they would realise that a point estimate is a value in which you have zero confidence.

🚨 Publication alert: update on the World Health Organization (WHO) #LivingGuidelines on drug treatments for COVID:

Highlights:
✅ The guideline development group (GDG) defined 1.5% as a new threshold for an important reduction in risk of hospitalisation in patients with non-severe covid-19 +

In this new article, we share our lessons learned with designing search strategies for methodological topics:
sciencedirect.com/science/articl…

Unusual news regarding clinicians' judgements:
sciencedirect.com/science/articl…