Harlan Campbell
@harlanhappydogPhD Statistics | meta-research | hypothesis testing | causal inference
Similar User
@fdabl
@mattansb
@the100ci
@annemscheel
@MicheleNuijten
@simongrund89
@brandmaier
@jazzystats
@jared_huling
@uygun_tunc
@laure_wynants
@RinkHoekstra
@LeonieVogelsm
@MatthewBJane
@smartin2018
Treatment switching in randomised controlled trials: Trial design, what to adjust for, how, and reporting guidelines. The DSU’s new TSD 24 provides an update to TSD 16 – out now! shorturl.at/uJKMO
There are no underpowered datasets; there are only underpowered analyses. statmodeling.stat.columbia.edu/2023/08/28/the…
🔔ICYMI: this #PhilTransA issue celebrates the work of Sir Adrian Smith, the President of the @royalsociety The issue explores the most significant current directions of #Bayesian inference. ow.ly/SeOP50NhCh0 @isi_wsc #isiwsc2023 #isiwsc
How can we start a conversation about #estimands with patient and public partners involved in #ClinicalTrials ? We spoke to some & co-developed a 2-page tool to explain the concept of an estimand available here: trialsjournal.biomedcentral.com/articles/10.11…
1-5 June /1-5 juin
Here's a bunch of good refs for "don't drop correlated predictors": Graham 2003 doi.org/10.1890/02-3114. Gregorich et al 2021 doi.org/10.3390/ijerph…. Morrissey & Ruxton 2018. doi.org/10.3998/ptpbio… Vanhove 2021 doi.org/10.15626/MP.20…
Now accepted for publication in Bayesian Analysis!
New preprint: "Defining a credible interval is not always possible with “point-null” priors: A lesser-known correlate of the Jeffreys-Lindley paradox" arxiv.org/pdf/2210.00029…
"Equivalence testing for linear regression" Now accepted for publication at Psychology Methods arxiv.org/abs/2004.01757
New preprint: "Defining a credible interval is not always possible with “point-null” priors: A lesser-known correlate of the Jeffreys-Lindley paradox" arxiv.org/pdf/2210.00029…
Replies to your question are great so far. We have a discussion about this that may be of interest in: open.lnu.se/index.php/meta…
🚨 #ResearchMethods webinar 🚨 May 17 UBC TI Methods Speaker Series: Diagnostic test accuracy network meta-analysis methods 🗣️Speakers: Drs. Areti-Angeliki Veroniki & Sofia Tsokani 🖊️Register: bit.ly/3JU1J5W #EvidenceSynthesis #SystematicReviews #DTA
Time for perhaps the most damning stat of all: One in 25 American five-year-olds today will not make it to their 40th birthday. No parent should ever have to bury their child, but on average across the US one set of parents from every kindergarten class most likely will.
At @MSFTResearch we had early access to the marvelous #GPT4 from @OpenAI for our work on @bing We took this opportunity to document our experience. We're so excited to share our findings. In short: time to face it, the sparks of #AGI have been ignited. arxiv.org/abs/2303.12712
Hello friends, #HappyPiDay 🥧 This is the only pie-ish chart you will find on @OurWorldInData Enjoy. ourworldindata.org/ghg-emissions-…
"Estimating marginal treatment effects from single studies and indirect treatment comparisons: When are standardization based methods preferable to IPTW?" arxiv.org/pdf/2301.09661…
United States Trends
Who to follow
-
Fabian Dablander
@fdabl -
Mattan S. Ben-Shachar 🎗️🇮🇱🇺🇦
@mattansb -
The 100% CI
@the100ci -
Anne Scheel
@annemscheel -
Dr. Michèle Nuijten
@MicheleNuijten -
Simon Grund @[email protected]
@simongrund89 -
Andreas M. Brandmaier
@brandmaier -
Lauren Kennedy
@jazzystats -
Jared Huling (@jaredhuling.bsky.social)
@jared_huling -
☠️ Duygu Uygun-Tunc ☠
@uygun_tunc -
Laure Wynants @laurewynants.bsky.social
@laure_wynants -
Rink Hoekstra
@RinkHoekstra -
Dr. Leonie Vogelsmeier
@LeonieVogelsm -
Matthew B Jané
@MatthewBJane -
Stephen Martin
@smartin2018
Something went wrong.
Something went wrong.