Gerda Wyssen
LightNews LightNews
banner
wyssen.bsky.social
Gerda Wyssen
@wyssen.bsky.social
110 followers 670 following 46 posts
postdoc | interested in how the brain makes sense of sensory information | vestibular input, mental imagery & spatial cognition | bayesian modelling | research methods & statistics | rehabilitation science | lego & sand...
Posts Replies Media Videos
Reposted by Gerda Wyssen
cghlewis.bsky.social
All we hear about now is LLMs and AI but the most frequently clicked links in the RDM Weekly newsletter are about basic data management (naming files, documentation, organizing code, etc.). So if you feel behind by what you see posted, please don't. These foundational skills still matter.
October 21, 2025 at 5:05 PM
Reposted by Gerda Wyssen
richarddmorey.bsky.social
For me this is a hard red line in psychological science. If you advocate the use of "silicon samples" you do not understand what it is we're supposed to be doing (and likely don't understand LLMs, or are a grifter). Luckily I haven't seen much of this among people I'd consider my peer group.
Except from Table 1 of Guest & van Rooij, 2025: 3) Displacement of Participants “I can use AI instead of participants to perform tasks and generate data.” The providence of the data used in these models indicates it is not ethically sourced, falling below standards for our discipline, involving sweatshop labour and no consent for private data used in experiments. The output can contain direct original input data (i.e. double dipping), but smoothed to remove outliers, conform to our pre-existing ideas of what it should look like (data fabrication), and all-round irreplicable. Psychology is meant to study humans, not patterns at the output of biased statistical models.
October 4, 2025 at 8:27 AM
Reposted by Gerda Wyssen
epiellie.bsky.social
If you’ve been following the RFK Jr autism news, then you’ve probably heard that there’s a systematic review “proving” Tylenol causes autism.

Here’s my review of that paper👇🏼

open.substack.com/pub/epiellie...
The best evidence Tylenol causes autism isn't great
On Monday, RFK Jr announced Tylenol ‘causes’ autism referencing three studies as evidence. Let's dive in.
open.substack.com
September 25, 2025 at 8:20 PM
Reposted by Gerda Wyssen
vincentab.bsky.social
Whoa—my book is up for pre-order!

𝐌𝐨𝐝𝐞𝐥 𝐭𝐨 𝐌𝐞𝐚𝐧𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐭𝐨 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭 𝐒𝐭𝐚𝐭 & 𝐌𝐋 𝐌𝐨𝐝𝐞𝐥𝐬 𝐢𝐧 #Rstats 𝐚𝐧𝐝 #PyData

The book presents an ultra-simple and powerful workflow to make sense of ± any model you fit

The web version will stay free forever and my proceeds go to charity.

tinyurl.com/4fk56fc8
September 17, 2025 at 7:49 PM
Reposted by Gerda Wyssen
imagingneurosci.bsky.social
Launched in 2023, Imaging Neuroscience is now firmly established, with full indexing (PubMed, etc.) and 700 papers to date.

We're very happy to announce that we are able to reduce the APC to $1400.

Huge thanks to all authors, reviewers, editorial team+board, and MIT Press.
September 5, 2025 at 2:59 AM
wyssen.bsky.social
Welcome to the Psychology Department. It has been 0 days since we discovered something existentially horryfing about bugs in our/their code that lets us question our whole reality... ;-)
xkcd.com Randall Munroe @xkcd.com · Sep 11
Biology Department

xkcd.com/3140/
Comic. [Building with large sign in front of it[ SIGN: Welcome to the *Biology Department* It has been [changeable sign: 3] days since we discovered something existentially horrifying about bugs that makes you question your whole reality
September 11, 2025 at 9:49 PM
Reposted by Gerda Wyssen
profandyfield.com
A shout out for @nrennie.bsky.social fab book on data viz! nrennie.rbind.io/art-of-viz/
The Art of Data Visualization with ggplot2
nrennie.rbind.io
September 5, 2025 at 11:17 AM
Reposted by Gerda Wyssen
improvingpsych.org
Is your preprint still pending moderation? See our recent post about how to make sure getting it approved is a smooth process:
bsky.app/profile/impr...

(pro tip: you can make edits even while it's in the moderation queue!)
improvingpsych.org Society for the Improvement of Psychological Science (SIPS) @improvingpsych.org · Aug 27
(1) Only submit to PsyArXiv if your contribution is within scope. Is it scholarly, and is it psychology?

(2) Include a title page with a descriptive title, all authors' names, and a contact email.
August 30, 2025 at 10:02 PM
Reposted by Gerda Wyssen
dermotlynott.bsky.social
Navigating Open Research: A Guide for Early Career Researchers. Great work from the CONUL Research Group. Free to download zenodo.org/records/1702... #irishResearch #openResearch
Cover matter: Navigating Open Research A Guide for Early Career Researchers From CONUL - consortium of national and university libraries #openResearch #irishResearch
September 2, 2025 at 9:36 AM
Reposted by Gerda Wyssen
histoftech.bsky.social
Steve Shirley escaped the Holocaust as a child & went on to found one of the earliest software startups. The really impressive part? She employed women programmers who had been pushed out of the workforce after having kids, & allowed them flexible, family friendly, work from home jobs—in the 1960s!
August 22, 2025 at 10:18 AM
Reposted by Gerda Wyssen
richarddmorey.bsky.social
Paper drop, for anyone interested in #metascience, #statistics, or #metaanalysis! @clintin.bsky.social and I show in a new paper in JASA that the P-curve, a popular forensic meta-analysis method, has deeply undesirable statistical properties. www.tandfonline.com/doi/full/10.... 1/?
Cover page for the manuscript: Morey, R. D., & Davis-Stober, C. P. (2025). On the poor statistical properties of the P-curve meta-analytic procedure. Journal of the American Statistical Association, 1–19. https://doi.org/10.1080/01621459.2025.2544397 Abstract for the paper: The P-curve (Simonsohn, Nelson, & Simmons, 2014; Simonsohn, Simmons, & Nelson, 2015) is a widely-used suite of meta-analytic tests advertised for detecting problems in sets of studies. They are based on nonparametric combinations of p values (e.g., Marden, 1985) across significant (p < .05) studies and are variously claimed to detect “evidential value”, “lack of evidential value”, and “left skew” in p values. We show that these tests do not have the properties ascribed to them. Moreover, they fail basic desiderata for tests, including admissibility and monotonicity. In light of these serious problems, we recommend against the use of the P-curve tests.
August 8, 2025 at 6:56 PM
Reposted by Gerda Wyssen
eikofried.bsky.social
Psychologists & related fields: what is a big methods question that you believe remains somewhat unanswered & that you'd love to see adressed? There may be an opportunity for a large-scale meta-science project with many teams trying to figure out a question.

Any thoughts welcome! #psychscisky
July 30, 2025 at 2:03 PM
wyssen.bsky.social
No LLM or trick or good teacher will save us from just often feeling very, very dumb while we are building expertise in something. We should teach students that this is a normal and even necessary part of learning.

Its either feeling stupid or remaining stupid.

There is no third box to tick.
August 1, 2025 at 9:26 AM
Reposted by Gerda Wyssen
eroston.bsky.social
10 years ago today, we dropped a thing that people still ask me about regularly.

The question "What's Really Warming the World?" still has the same answer.

With Blacki Migliozzi, in conversation with NASA GISS geniuses @climateofgavin.bsky.social and @drkatemarvel.bsky.social
🎁🔗
What's Really Warming the World?
What's Really Warming the World? Climate deniers blame natural factors; NASA data proves otherwise
www.bloomberg.com
June 24, 2025 at 1:12 PM
Reposted by Gerda Wyssen
vincentab.bsky.social
🚨 Big milestone for Rdatasets 🚨

The web archive now hosts 3400+ free and documented CSV datasets. Fantastic for teaching and testing!

And {Rdatasets} is a new #RStats 📦 for easy download and search

Web archive: vincentarelbundock.github.io/Rdatasets

R 📦: vincentarelbundock.github.io/Rdatasetspkg
June 6, 2025 at 5:39 PM
Reposted by Gerda Wyssen
andrew.heiss.phd
Updated my "AI, LLMs, and bullshit" mini-lecture post in my dataviz class with a new section on vibe coding datavizs25.classes.andrewheiss.com/resource/ai-...
Vibe coding and learning Remember that LLMs are (philosophical) bullshit machines. They don’t care if the answer if gives you is wrong or right. They don’t care if the code runs or not. All they care about is if the answer looks plausible. That said, in part due to the massive amount of publicly available code that’s inside their training data, LLMs can work okay with code in limited circumstances. Think of them as fancy documentation—if a programming language or package has good documentation with lots of good examples online, the stuff that LLMs generate about it will generally have good coverage and won’t be completely made up. They work well enough that a whole new approach to programming has emerged: vibe coding. When vibe coding, you essentially tell an LLM what you want it to make and then let it actually build the whole thing. Some code editors actually allow LLMs to create and edit files directly on your computer. Like, you can say Make a website that has a login page where users can log in and then create and edit blog posts. Create a theme for it that is mostly blue, but with some nice contrasting colors, and use a warm, friendly sans serif font. Add some photos from Flickr too. … and it will attempt to do that, creating all the necessary files and code. It feels neat and magical to code without coding. If you know what you’re doing, and you mistrust everything the LLM spits out, and hand-check everything it says, vibe coding can save you some time. HOWEVER it is (1) potentially dangerous, and (2) bad for learning. Danger! Because LLMs are designed to make plausible looking code, they can reference external packages that don’t exist. For instance, you might want to make a lollipop chart, and it’ll say something like Certainly! First, run remotes::install_github("someone/gglollipop") and then run library(gglollipop) to load it. BUT GUESS WHAT. There is no package named {gglollipop}. It’s not a thing. Malicious actors also vibe code and look for the names of packages that LLMs think should exist, then they go and create those packages themselves, but include malware in those fake packages. If you’re using an editor that allows LLMs to make changes to your computer, it can run all this code without you knowing what happens and bad things can happen. Additionally, vibe-coded code can run well but be full of security vulnerabilities and issues and inefficiencies and bugs. The code it generates is essentially an average of all other code online—it will have bugs and security issues. It’s also incredibly easy to accidentally expose private information to LLMs, like feeding them passwords, usernames, private data, and so on, especially if you’re mindlessly generating and running code. Always distrust and be suspicious about all code that LLMs generate. Bad for learning! Some people claim that vibe coding helps them learn how to code. This is most likely not the case—pure vibe coding likely hurts learning. Think of learning to code like learning a language. You could try to learn French by watching hours and hours of French movies, and you’d certainly pick stuff up, but you won’t learn nearly as well as you would by taking a dedicated French class. You need the foundation first. If you take a few years of French classes and then watch hours and hours of French movies, you’ll learn a lot. If you jump right into a pure media-based approach to learning, it’ll be detrimental to learning the language. Recent research explores this idea with LLMs: Students who substitute some of their learning activities with LLMs (e.g., by generating solutions to exercises) increase the volume of topics they can learn about but decrease their understanding of each topic. Students who complement their learning activities with LLMs (e.g., by asking for explanations) do not increase topic volume but do increase their understanding. We also observe that LLMs widen the gap between students with low and high prior knowledge. (Lehmann, Cornelius, and Sting 2025) Prior knowledge is essential if you want to do any code-related stuff with LLMs, and even then, LLMs are helpful when asking for explanations (e.g. “This code works, but I don’t know why! Can you explain what’s happening with geom_point() here?”), but far less helpful for learning than just generating plausible-looking answers. I can typically tell when you submit code generated by an LLM; it has a certain vibe/style to it and often gives you extraneous code that you don’t actually need to use. Like this—this comes right from ChatGPT: # Load the required libraries library(dplyr) # Read a file named cars.csv into the R session data <- read.csv("data/cars.csv") # Calculate the average value of cty by class average_cty_by_class <- data %>% group_by(class) %>% summarize(average_cty = mean(cty, na.rm = TRUE), .groups = "drop") # Show the results print(average_cty_by_class) The “tells” Here’s how I can tell that that ↑ code comes from an LLM: Comments at every stage read.csv() instead of read_csv(), The older %>% pipe instead of the newer |> pipe na.rm = TRUE inside mean() .groups = "drop" inside summarize() Using print() to show the created object In general, don’t ever just copy/paste from ChatGPT and hope it runs. If you do use these tools, use them to ask for explanations. Make sure you know what every line of code is doing. For example, if it spits out summarize(average_cty = mean(cty, na.rm = TRUE), .groups = "drop"), and you don’t know what those na.rm = TRUE or .groups = "drop" things mean, look at the help page for mean() and see what na.rm actually does so you can decide if you really need to use it or not, or ask the LLM why it included it. I will call out code that looks vibe-coded in your assignments. Please don’t do it.
June 5, 2025 at 3:04 PM
wyssen.bsky.social
I now understand better why wiener waffeln exist.... every time my initial values are rejected I eat one
#rstats #brms #rstan #ddm
Code for fitting a ddm model including wiener as a link function and in front of the screen some wiener waffel cookies
May 28, 2025 at 9:14 AM
Reposted by Gerda Wyssen
khinsen.net
The whole notion of "research outputs" is a fallacy. Science doesn't make products. It's a process that maintains and updates a web of facts, theories, tools, techniques, etc. You can interrogate this web at any time but it doesn't deliver products for out-of-context consumption.
May 28, 2025 at 5:32 AM
wyssen.bsky.social
#statsedu Any good ideas how to archive teaching websites for students? Does it make sense to save it as OER? (Its a statistics/r introduction website built with quarto)
May 27, 2025 at 12:08 PM
Reposted by Gerda Wyssen
rmcelreath.bsky.social
Let’s achieve a research culture that supports this reasonable and humane anthem
amreibahr.bsky.social Amrei Bahr @amreibahr.bsky.social · May 26
Ich möchte nicht exzellent sein. Ich möchte keine Spitzenforschung machen. Ich möchte einfach meine Arbeit tun — ohne Befristungs-Schleudersitz, ständigen Bewerbungszwang, wechselnde Arbeitsorte, zig Stunden pro Woche in verspäteten Zügen & den wiederholten Verlust sozialer Kontakte. #IchBinHanna
May 26, 2025 at 3:45 PM
Reposted by Gerda Wyssen
devezer.bsky.social
OK I had announced this before but forgot to say that Andrew Gelman would be joining Nancy Cartwright and myself as well. Short idea talks, lots of panel discussion and Q&A.

Join us on April 25th to discuss RCTs, replications, and scientific inference.

sites.google.com/view/cepbi/t...
Mark your calendars for our next online tandem talks in 2025: Experiments, Causal Inference, and Limits of Evidence APRIL 25 at 10Am ET Nancy Cartwright (Durham University, University of California, San Diego) Berna Devezer (University of Idaho) Andrew Gelman (Columbia University)
April 8, 2025 at 2:59 PM
wyssen.bsky.social
Does the strong magnetic field and the resulting vestibular stimulation im MRI scanners influence cognitive processes?
We found evidence suggesting yes.. but only for tasks relying on own body position.
May be relevant for some fMRI studies on spatial cognition, especially in 7T!
#fmri #neuro #mvs
psyarxivbot.bsky.social PsyArXivBot @psyarxivbot.bsky.social · Mar 31
Cognitive functions in ultra-high magnetic fields: Specific Influence of Magnetic Vestibular Stimulation on Mental Rotation in 7T MRI: https://osf.io/fpq5v
March 31, 2025 at 4:22 PM
Reposted by Gerda Wyssen
dingdingpeng.the100.ci
Are you interested in age or cohort or period effects? I have just updated my primer on the topic!
Now with a new framing, a handy flow chart to determine which approach may be suitable, and a new empirical example. What do people in Germany think about mothers who work? osf.io/preprints/ps...
Flow chart: Different ways to deal with the age-period-cohort identification problem. Figure with multiple panels showing mean scores over age or survey year, split by cohort, survey year or age. Figure with a canonical solution line and nonlinearities extracted by the bounding analysis approach by Fosse & Winship. Figure showing the resulting bounds on the age, period, and cohort effects.
January 28, 2025 at 2:48 PM
wyssen.bsky.social
Interested in vestibular cognition?
We replicated the findings of van Elk & Blanke (2014) on the influence of passive motion on mental rotation.

osf.io/preprints/ps...
OSF
osf.io
March 17, 2025 at 9:21 AM
Reposted by Gerda Wyssen
ardenthistorian.bsky.social
Remember that this is the message behind every single Nazi salute. It is unconscionable to downplay or minimise it (as a „mysterious gesture“ or „trolling“). Every Nazi salute carries a murderous message. Fail to call that out, and you are complicit. Don’t think they won’t come for you, too.
lioneltrolling.bsky.social John Ganz @lioneltrolling.bsky.social · Feb 23
To me, a Nazi salute means, "I want to murder your family." There can be no irony about it: It puts deep anger and hatred in my heart to see it done and I will never forgive anyone who justifies or minimizes it.
February 24, 2025 at 1:18 AM