Martina Sladekova

Join the RoSE Network on July 31st for our free, international, statistics education research conference! Keynote speaker Dr. Iddo Gal asks "What research is needed in statistics education, and why?" You can learn more by connecting with us online by searching RoSE Network on X ,Slack, Bluesky, Mastodon, LinkedIn, and Youtube, or check out our website: www.rose-network.org!

Excited for our #StatsEd conference on July 31st? You can register to attend for ✨ free ✨ by clicking here: bit.ly/roseconferen... - Don't miss a chance to connect with other statistics education researchers from around the world!

GitHub - njudd/ggrain: {package} Make beautiful Raincloud plots in R! {package} Make beautiful Raincloud plots in R! Contribute to njudd/ggrain development by creating an account on GitHub.

In psychology, CIs are pretty common so I guess it depends on the discipline.

I love raincloud plots - it's a nice way to combine raw data distributions + summary stats in one plot. Here's an R package with some examples: github.com/njudd/ggrain

I'd use confidence intervals because they're more useful for inference 🤷. But if both SD and SEM are relevant and needed, why not plot both? You could try something like a raincloud plot with the SD displayed on the "cloud" and SEM around the mean.

Psych Stats Instructors: please consider participating in a 15-min anonymous survey about best practice and teaching methods. Closes May 31st. For details see: ryersonpsych.co1.qualtrics.com/jfe/form/SV_...
Sharing appreciated!

From NYT article about the increasing use of AI in the classroom: “Writing is one of the most challenging tasks for students, which is why it is so tempting for some to ask A.I. to do it for them. In turn, A.I. can be useful for teachers who would like to assign more writing, but are limited in their time to grade it.”

Why even have a brain, any ideas, any ability to express them, any kind of communication with other people, any desire to solve problems or invent anything, any reason to learn, any use for your eyes or your heart, or any reason to teach or create

I do descriptive stats first with psych students - show what kind of measures can be used to summarise data (central tendency and dispersion), then show how to plot them and how _not to_ plot them.

Just above The Long Man of Wilmington (walked from Eastbourne). Devil's Dyke is on the list next time we get weather like this.

Post a photo you took with no context to bring some zen to the timeline.

There’s still time to sign the open letter

docs.google.com/forms/d/e/1F...

Parallelization in purrr — parallelization purrr's map functions have a .parallel argument to parallelize a map using the mirai package. This allows you to run computations in parallel using more cores on your machine, or distributed over the ...

Parallelization just landed in the dev version of purrr: purrr.tidyverse.org/dev/referenc...

Really pleased that the mirai framework makes this possible.

Huge credit to the tidyverse maintainers @hadley.nz @lionelhenry.bsky.social and @davisvaughan.bsky.social !

#rstats #tidyverse

As someone who barely posts, I've narrowed it down to this: bsky.app/profile/prof...

Trying to compile a list of people with active pedagogic interests in teaching statistics go.bsky.app/Qg6YSq6

Thank you!(:

What's the moment of luck that's had the biggest impact for your academic career? For me, it was how I wouldn't have gotten a PhD fellowship if it wasn't for the 1st-ranked person declining, which meant that I was awarded the fellowship as 2nd-ranked applicant. That was my last shot at a PhD.

Concerned Tom meme with text "My computer watching me put the kettle on as I hit run on part 2 code"

Brute-forcing my way through Day 7 of #AdventOfCode with #rstats:

github.com/martinaslade...

Day 6 - part 1 only ⭐ 🏳️
github.com/martinaslade...

Part 2 will need to wait until my end-of-term broken brain recovers some capacity to function (or not)
#AdventOfCode

Day 5 #AdventOfCode using #rstats:

github.com/martinaslade...

It doesn't count as an explicit loop if it's wrapped in a function, right...?

Day 4 #AdventOfCode, this time combining #rstats and chaos (and some purrr again):

github.com/martinaslade...

#AdventOfCode Day 3: github.com/martinaslade...
Reluctantly grappling (grepling?😏) with REGEX using #rstats and #tidyverse.

Happy to have been a small part of this NEW PAPER by @beccalouisedean.bsky.social✨ She synthesised evidence to find out whether young people's self-perceptions change in response to treatment for depression. Check it out here 👉 authors.elsevier.com/c/1kBub~0r1w3cL

Day 2 of #AdventOfCode using #rstats and #tidyverse, this time full of (possibly unnecessary) purrrmagedon:
github.com/martinaslade...

I'd have to be coding it in Rust for that to be true 🥸

My #AdventOfCode Day 1 solutions with a chaotic combination of tidyverse and base R: github.com/martinaslade...
Last time I attempted these was 3 years ago and rage-quitted about half-way through. I look forward to questioning my competence daily over the next three weeks 🔥👨‍💻🎄

Full version with linking chapters now available:

sussex.figshare.com/articles/the...

If you find typos... don't tell me.

Wherever possible, data and materials are openly available (access through the preprints). I’ll post the full version of the thesis after finalising corrections.

Finally, massive thanks to @Dom_Makowski and @alyssacounsell.bsky.social for a fair and thought-provoking viva.

Chapter 6 simulates the conditions from Chapter 5 and evaluates commonly used OLS models, plus several robust estimators:
doi.org/10.31234/osf...
P.S.
ANOVA is not robust.

Chapter 5 looks at residual distributions out in the wild and summarises the conditions psychology researchers should realistically expect when analysing data:
doi.org/10.31234/osf...

Chapter 4 was a several months long detour where we developed a measure for quantifying heteroscedasticity in models with continuous predictors:
doi.org/10.31234/osf...
(version with R package and code tutorial coming soon)

Chapter 3 had similar objectives as chapter 2, but we asked researchers to complete two analytic exercises to see whether they would check assumptions or apply robust methods:
doi.org/10.31234/osf...

Chapter 2 is a self-report survey looking at researchers’ understanding of model assumptions and related practice:
doi.org/10.31234/osf...