Yes, we should really start calling them TIE fighter plots! Can we do this please?

#episky #statsky #epimethods

Ending publication bias: A values-based approach to surface null and negative results Sharing knowledge is a fundamental principle within the scientific community, yet null and negative results are still being underreported. This Consensus View discusses the problem of such publication...

Direct link to the paper does not work (has an extra bracket at the end).

journals.plos.org/plosbiology/...

Detection Bias: Seek, and Ye Shall Find It’s September which means RFK Jr will soon be releasing his promised report on the ‘causes’ of autism. Until then, we're learning about important biases.

All September, I'm explaining common research biases.

Today is detection bias. Which is so simple even Trump understands it!

Read here: open.substack.com/pub/epiellie...

Proposal for how to fix family wise error rates.

For every uncorrected p value you must add an extra letter to the claim.

“Eating chocolate maaaaaaaaay be associated with lower rates of stroke”

A mixed-methods study on the recruitment of patients from ethnic minority groups to clinical trials in a central London teaching hospital Additional research is needed to fully understand barriers in recruitment to clinical trials and how these might affect different ethnic groups. The a…

Vindrola-Padros et al: Mixed-methods study on improving recruitment of ethnic minority groups for clinical trial

Beneficial: Access to information about research & data usage, translated materials, interpreters during recruitment, greater ethnic diversity in study teams

How to Live Forever (or at least make it seem like you do!) It’s September which means RFK Jr will soon be releasing his promised report on the ‘causes’ of autism. Until then, we're learning about important biases.

Today's post is all about how a badly designed study can make it look like people live forever.

And how, if you only apply this to one group, you can essentially guarantee any study result you want. 😬

open.substack.com/pub/epiellie...

Improving Representation of Underserved Populations in Cardiovascular Research | Journal of the American Heart Association

Correct DOI for Loh et al is: doi.org/10.1161/JAHA...

Loh et al: Narrative review on strategies to improve representation of underserved populations in cardiovascular research

Most (all?) of the discussed problems and strategies will apply to other fields of clinical research as well.

doi.org/10.1161/JAHA...

Trends in the Distribution of P Values in Epidemiology Journals: A Statistical, P-Curve, and Simulation Study Abstract. Epidemiologists have advocated for reporting confidence intervals and deemphasizing P values to address long-standing concerns about null-hypothe

Less p-hacking, better powered studies, or both?

Paper looking at the distribution of p-values in articles published in four #episky journals between 2000-2024.

#epimethods #statsky

doi.org/10.1093/aje/...

Vibe coding is coloring by numbers at best.

Strategies to optimize the engagement of culturally and linguistically diverse populations in cardiac research: a systematic review AbstractAims. Culturally and linguistically diverse (CALD) populations remain underrepresented in cardiovascular disease (CVD) research despite their highe

Abou Chakra et al: Systematic review on strategies to increase engagement of CALD populations in cardiac research.
Community outreach/snowball recruitment, multilingual invitations/material, cultural competency of staff seem to improve recruitment.

doi.org/10.1093/eurj...

... and to better hide it if it happens anyway.

Reporting Participation in Epidemiologic Studies: A Survey of Practice Abstract. Self-selection bias may threaten the internal validity of epidemiologic studies. Studies with a low level of participation are particularly vulne

Classic paper by Morton et al. that will have its 20th anniversary later this year. Core message: reporting of response was poor and participation was on the decline back then.
Would be interesting to know whether reporting improved now that STROBE and CONSORT are standard.

doi.org/10.1093/aje/...

Thread with a loose collection of papers on recruitment for population-based research, reporting standards/practice, and approaches to increase diversity in samples and engagement of populations underserved by health research and services.

#episky #epidemiology #publichealth #medsky #statsky

ggplot2 4.0.0 A new major version of ggplot2 has been released on CRAN. Find out what is new here.

I am beyond excited to announce that ggplot2 4.0.0 has just landed on CRAN.

It's not every day we have a new major #ggplot2 release but it is a fitting 18 year birthday present for the package.

Get an overview of the release in this blog post and be on the lookout for more in-depth posts #rstats

Code in the R script that I have been using for years to monitor recruitment in a long-running study.

#EpiSky #StatSky #rstats

In my day there was no autism... and we walked to school uphill... both ways... in the snow... It’s September which means RFK Jr will soon be releasing his promised report on the ‘causes’ of autism.

RFK Jr loves to say that there was no autism when he was a kid. And technically he's right. But he's also making a classic error!

open.substack.com/pub/epiellie...

Prevent Illness with this One Weird Trick: Dying. It’s September which means RFK Jr will soon be releasing his promised report on the ‘causes’ of autism. Let's prepare by learning type of bias.

Today's E is for Epi reveals the one weird trick that prevents all illness!
Check it out here👇
open.substack.com/pub/epiellie...

Confounding by Indication: A Research Bias You Should Know It’s September which means RFK Jr will soon be releasing his promised report on the ‘causes’ of autism. We can prepare by learning some key types of research bias.

RFK Jr has promised to release a report on the causes of autism in September. To prepare, it's a good idea to make sure we know what the common types of observational research biases are. First up: confounding by indication.
Read more here: open.substack.com/pub/epiellie...

📌

https://hsph.harvard.edu/research/causalab/seminars/

The CAUSALab Methods Series @ki.se is back!

Fall 2025 lineup kicks off Sep 23 with Vanessa Didelez (BIPS), “Causal mediation and separable treatments in time-to-event analyses.”

All talks are virtual, except for Nov. 4, 2025 hybrid session.

Learn more & register:
hsph.harvard.edu/research/cau...

When using observational data for #causalinference, the choice isn’t between emulating or not emulating a #TargetTrial, but between reporting or not reporting the target trial that we are emulating.

For those who prefer to be explicit about what they do, we have developed the TARGET Statement 👇

In rare moments of reflection, I am always amazed how much I trust that R packages do what they claim to do, especially if their version number starts with a zero. 😬

#R #data #epimethods

STROBE-Equity Extension Checklist and Elaboration This consensus statement extends the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) reporting guideline to provide additional guidance for reporting on health equity dat...

jamanetwork.com/journals/jam...

The TARGET 2025 guideline provides recommendations for transparent reporting of observational studies emulating a target trial to estimate causal effects, enhancing clarity and interpretation.

#PRC10 @peerreviewcongress.bsky.social

ja.ma/41w9rwW

A nasal spray reduced the risk of Covid infections in a double blind, placebo controlled randomized trial
jamanetwork.com/journals/jam...