My slightly biased take on this is that you could consider the easystats ecosystem as an alternative (mostly {datawizard} 📦for data wranling, the rest for analytic workflow/tasks), which is also very easy to learn and not that much overload.
I think the basics of tidyverse are easy to understand for people new to R or not much experienced. Syntax becomes more complicated for special features, but for basic data wrangling, tidyverse is easy to understand. You just need to teach that every pipe-chain needs to end with `as.data.frame()`. 😘
I mean, it's completely fine to say there's a 95% chance that a tibble will not behave as a data frame.
(you can't deny that this was an epic example, incorporating baseR-tidyverse flamewar with frequentist-CI-interpretation-controversial)
I don't think that bsky.app/profile/stre... is controversial, either. 😎
But it's not that controversial, it's just the distinction between the process (aleatory probability - which collapses to 0 or 1, once you know the result) and our beliefs (epistemic probability), see doi.org/10.1016/j.js.... Thus it's fine to say there’s a 95% chance my interval contains <whatever>
I just realized the small post-it in the left corner... 🤣 maybe better to see in this hires-image
I'm pasting one of these memes into every manuscript where I'm asked to write the methods section after I did the analyses.
Screenshot von Video von Paul Sies zu „auch in der Nazizeit war Spargelzeit“
Können wir bitte dieses Lied jeden Abend einmal kurz vor der Tagesschau in der ARD spielen? youtu.be/w_0cSgsC460?si
St. Pauli!
Maybe Schweder/Hjort are also of interest for you, at the end of these docs are some references:
easystats.github.io/parameters/r...
Just interpret it as a probability interval (link.springer.com/article/10.1...)
Computation time is no issue unless you run a Bayesian model on data with more than 10k observations on a single computer. 😜
Mostly agree, but it's *me* who can pin down issues, often not the casual user. But still, I find it strange that a package "by design" breaks code that is supposed to work otherwise, and that worked for decades. You can't blame other authors' code for perfectly running with "real" data frames.
Sometimes, package like modelling packages initially work with tibbles, but then other functions (simple toy-example: `coef()`) do not. Then you start searching *your* code for issues, until you realise it's the tibble that cannot be processed in the *others* code.
We often got issues filed on GitHub, where the source of the error weren't our packages/code, but a tibble that claimed to behave like a data frame, but simply does not. No(!) helpful error message at all. That's something for debugging masochists.
Since I had some experiences with tibbles (the colleague did not and thought function doesn't work), it meanwhile doesn't take that long to figure it out. Note the `as.data.frame()`.
One of the many, many issues I faced with tibbles in my 30 years of programming and 10 years of R experience (not joking, it's almost the same dates). What is wrong here?
Debugging issues that arise from tibbles can be absolutely painful, when they "hide behind" data frame.
@vincentab.bsky.social, the guy whose days have more than 24 hours. (ok, altdoc is mainly @etiennebacher.bsky.social, with support from Vincent)
Dear U.S. government...
You should add a critical section here:
easystats.github.io/modelbased/a...
(generating notebook lm podcast for the bike ride to the office)
You mean `model_performance()`, not `model_details()`? But we are very pleased that the easystats packages are becoming increasingly noticed 🙂
Sure, will do!
Hm, doesn't work for me. I'm using the latest daily build:
Positron Version: 2026.03.0 (system setup) build 14
Code - OSS Version: 1.106.0
Date: 2026-02-03T08:15:39.951Z
Electron: 37.7.0
Chromium: 138.0.7204.251
Node.js: 22.20.0
V8: 13.8.258.32-electron.0
OS: Windows_NT x64 10.0.26200
GitHub integration. Other than that, it's like windows 95 (RStudio) vs Windows 11 (Positron) 😉
One of the few things you have to get used to is debugging. You cannot use breakpoints (yet) and must use browser(), but you get used to it fast. I have now uninstalled RStudio because I haven't started it for months...
I think there's an option to activate RStudio shortcuts, but since I was already using VSCode instead of RStudio before Positron came out, I completely setup my own shortcuts (or modified shortcuts so they matched with those from RStudio, partly).
You should switch to Positron! (and here's how to do it there)
