Cath Blatter
LightNews LightNews
banner
cathblatter.bsky.social
Cath Blatter
@cathblatter.bsky.social
620 followers 250 following 0 posts
RN & researcher | workforce & resident safety in long-term care | 💚 #RStats & #DataLiteracy | ⚽️, mountains & the nordic outdoors | 🏳️‍🌈 | 🦣@cathblatter@mstdn.nursing.unibas.ch
Posts Replies Media Videos
Reposted by Cath Blatter
mattansb.msbstats.info
I can't be the only one, right?

#statsmeme
Elmer Fudd, but he's in front of a laptop, looking at a spaghetti plot, so it's lmer Fudd.
September 27, 2025 at 3:58 PM
Reposted by Cath Blatter
karaman.is
Explore Scotland’s tallest Munros and Munro tops with this week’s #TidyTuesday

Code: github.com/gkaramanis/t...

#RStats #dataviz
The plot displays the 20 highest Munros and Munro tops in Scotland. The main chart is a vertical bar plot showing mountain names and their heights in meters and feet, with striped bars indicating Munro tops. The tallest peak, Ben Nevis, is highlighted in both meters and feet. An inset map of Scotland shows the geographic locations of all Munros, with Ben Nevis marked in red and labeled.
August 24, 2025 at 1:41 PM
Reposted by Cath Blatter
dingdingpeng.the100.ci
Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...
Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities Abstract Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models). Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve. A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals). Illustrated are 1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals 2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and 3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.
August 25, 2025 at 11:49 AM
Reposted by Cath Blatter
christosargyrop.bsky.social
Dunning-Kruger curve, with and without AI.

The era of Automated General Idiocracy is rising

From:
x.com/ryzerth/stat...
August 24, 2025 at 9:53 PM
Reposted by Cath Blatter
lexbouter.bsky.social
Nice! My preprint with short personal reviews of 31 novels on #ResearchIntegrity now published open access in Chinese.
English preprint: bit.ly/409E5ff
Chinese publication: bit.ly/4osKFYp
@peerreviewcongress.bsky.social @wcrifoundation.bsky.social @nrin-integrity.bsky.social @retractionwatch.com
August 12, 2025 at 6:59 AM
Reposted by Cath Blatter
reproducibilitea.org
📚 Resources - a new section on our website
reproducibilitea.org/resources

This section includes resources published by ReproducibiliTea journal clubs:
📽️ video recordings of past events
📊 presentations
📄 reading lists
✍️ blogs
Resources
ReproducibiliTea - Journal Clubs for Open Science
reproducibilitea.org
August 14, 2025 at 11:47 AM
Reposted by Cath Blatter
fguelzau.bsky.social
Nice figure! There's also a helpful blogpost by @vincentab.bsky.social that discusses different ways to include age as a predictor.
What to do with age? Linear, Discrete, Both, or Spline – Vincent Arel-Bundock
arelbundock.com
July 8, 2025 at 12:18 PM
Reposted by Cath Blatter
davisvaughan.bsky.social
Air (our extremely fast R formatter!) now has official documentation for both Neovim and Helix, thanks to our awesome community (Tamás Plaszkó, Philippe Massicotte, @mmuecke.bsky.social, and Tymoteusz Makowski)!

Neovim: posit-dev.github.io/air/editor-n...
Helix: posit-dev.github.io/air/editor-h...
davisvaughan.bsky.social Davis Vaughan @davisvaughan.bsky.social · Feb 21
@lionelhenry.bsky.social and I are so excited to finally announce Air - an extremely fast R code formatter! 🎉

With Air, you'll never need to worry about styling your #rstats code ever again. All you need to do is save, and Air takes care of the rest.

www.tidyverse.org/blog/2025/02...
Air, an extremely fast R formatter
We are thrilled to announce Air, a new R formatter.
www.tidyverse.org
March 4, 2025 at 2:24 PM
Reposted by Cath Blatter
sungkim.bsky.social
Microsoft Data Formulator

Data Formulator is an AI-powered tool for analysts to iteratively create rich visualizations. Data Formulator combines user interface interactions (UI) and natural language (NL) inputs for easier interaction.

github.com/microsoft/da...
February 11, 2025 at 5:25 AM
Reposted by Cath Blatter
leni.bsky.social
In case you havenʼt seen it yet, this website is such a great resource for all of us researchers and teachers working on and discussing technology and society:

Calculating Empires – A Genealogy of Technology and Power since 1500
calculatingempires.net
Calculating Empires: A Genealogy of Technology and Power since 1500
Explore how technical and social structures co-evolved over five centuries in this large-scale research visualization.
calculatingempires.net
November 22, 2024 at 2:39 PM
Reposted by Cath Blatter
stefan-sell.bsky.social
Lea Bergmann et al. (2024): Nursing Home Shortage and Hospital Bed-Blocking: www.rwi-essen.de/fileadmin/us...
November 20, 2024 at 6:43 AM
Reposted by Cath Blatter
pdalgd.bsky.social
#rstats
R version 4.4.2 "Pile of Leaves" (source version) has been released. (You can find it in cran.r-project.org/src/base/R-4/, or wait for CRAN to be updated.)
October 31, 2024 at 9:57 AM
Reposted by Cath Blatter
jhelvy.bsky.social
Our #rstats survey platform #surveydown is taking off! 🚀

53 stars on Github and counting! Thanks for everyone giving it a try, we've made tons of improvements in the last month or so!

surveydown.org
Line chart showing start count over time. Rapid increase started in last summer and still going!
October 13, 2024 at 5:32 PM
Reposted by Cath Blatter
xkcd.com
Iceland xkcd.com/2874
December 30, 2023 at 12:07 AM
Reposted by Cath Blatter
lizziereed.bsky.social
NOBODY CARES WHAT FORMAT THE REFERENCES ARE IN AS LONG AS THEY CAN FIND THE PAPER.

This message brought to you by: the wasted hours of reformatting references by journal style.
November 28, 2023 at 10:16 AM
Reposted by Cath Blatter
thinkacademia.bsky.social
NO-vember reminders!

It's fine to say no to:
- working unreasonably long hours/weekends
- taking on more work than you have time/energy for
- spending time with people/on things that don't make you happy

#AcademicMentalHealth #PhDVoice

Image credit: @academeology via Twitter
This is an illustration titled, "No"vember - It is time to start saying NO to... by @academeology on Twitter. It is time to start saying NO to... - taking on more work and new projects - unpaid labour and work you don't get credit for - working at night and on weekends - overly long hours at your desk - people/places/things that steal your joy - anything that burns you out
November 13, 2023 at 3:38 PM
Reposted by Cath Blatter
cghlewis.bsky.social
Feeling grateful for {janitor} (as usual) for taking my overwhelming data frame from 1035 variables to a more manageable 58 variables. #rstats
October 31, 2023 at 4:14 PM