Daniel Dunleavy

Job opportunities at Retraction Watch Here are our current open positions: Intern, Medical Evidence Project Editor, Medical Evidence Project Staff reporter, Retraction Watch Learn more about The Center for Scientific Integrity, and abo…

Hello.

The MEP is hiring an intern (a paid one, not an 'ooh ooh think of the experience' one)

retractionwatch.com/job-opportun...

Feel free to direct this to anyone interested. I think it will fill quickly so pitter patter.

Come join our team!

Hey! If you haven't seen them before, please enjoy these slides from @djnavarro.net (drawing on @jennybryan.bsky.social) on thoughtful file organization/naming - again, something that's vital but often not explicitly taught.

djnavarro.net/slides-proje...

Recently, I've spent time reflecting both on the type of scholarly work I'm pursuing and how I present such work

Below, I muse about how I can better support non-commercial and scholar-led publishers and journals

#OpenAccess #ScholarlyPublishing #DeSci

www.researchhub.com/post/4028/br...

Powerful Myths: Common Misconceptions About Statistical Power Lukas Lengersdorff and Claus Lamm discuss three misconceptions that stand in the way of an informed discussion.

Three Myths About Statistical Power

🔹️ Myth 1: Power is an objective feature

🔹️ Myth 2: With low power comes low credibility

🔹️ Myth 3: High power protects against questionable research practices

BSky author: @clauslamm.bsky.social

I ended up having a lot of trouble with the geom_flags function in "ggimage", but found a workaround.

Code is available here: github.com/dunldj/Tidy-...

I appreciate any feedback!
#rStats #DataViz

For #TidyTuesday Week 3 (The History of Himalayan Mountain Expeditions), I chose to make a bar chart for the top 15 countries, based on number of claimed expeditions completed

I found this a good excuse to learn how to add country flags to a chart (as well as learn about the "countrycode" package)

Looks like we had a similar approach on this one!

For #TidyTuesday Week 2 (posit::conf talks) I chose to make word clouds from presentation abstracts for the 2023 and 2024 conferences. To do so, I primarily relied on the Tidytext & Wordcloud2 packages.

Code is available here: github.com/dunldj/Tidy-...

I appreciate any feedback!
#rStats #DataViz

ERROR is our scientific bug-bounty program.

We pay reviewers and authors of impactful published articles to do a deep dive on results, data, code, etc to check for errors.

Our second report of 2025 (and my first acting as Recommender for the review) is out now!

Looking forward to digging into this piece by Bruce Thyer #SocialWork #SocialWorkResearch

"Don't Waste Your Time Doing Social Work Research!"

doi.org/10.1177/1049...

Alright it's here! Where we push back against the exploratory-confirmatory distinction that's become canonized in metascience and talk about what we think exploratory research (including exploratory experimentation and modeling) means and why our view is incompatible with 'unplanned data analyses'.

Ignoring measurement reliability is a real-life horror story Why we need a measurement reliability crisis in psychology, now

Is there a stats/methods paper or book that you return to over and over again? I've found myself rereading this blog post by Sam Parsons every few years. It hits just as hard each time

medium.com/@Sam_D_Parso...

Lot of cool books continuing to come out for those interested in the history and ideas of logical empiricism.

Among them: Alan Richardsons' Logical Empiricism as Scientific Philosophy, Sahotra Sarkar's The Vienna Circle: The Story of Logocal Empiricism, and Adam Tuboly's Otto Neurath in Britain.

Thanks! And that's a fair point. Honestly, I kind of forgot how to separate things out by sex and cancer type without it grouping weird. But I've mucked around and figured it out. Here's an updated version with less going on in the background.

Code: Additional code added in the original link

Tidy-Tuesday-2025/Week 1/tidy-tuesday_1.R at 7cc3455f94b2acc92882c614b1a923c11a7dbdf2 · dunldj/Tidy-Tuesday-2025 Tidy Tuesday 2025 output. Contribute to dunldj/Tidy-Tuesday-2025 development by creating an account on GitHub.

Code is available here: github.com/dunldj/Tidy-...

I appreciate any feedback!

#TidyTuesday #RStats

For my first #TidyTuesday of 2025 (Week 1-Bring your own data), I chose to visualize cancer incidence in the U.S. using data from the National Cancer Institute’s SEER Program. I chose the 4 most common cancers and attempted to visualize their incidence by sex, for years 1975-2021.

#RStats #DataViz