Matt Williams
LightNews LightNews
matthewmatix.bsky.social
Matt Williams
@matthewmatix.bsky.social
1.7K followers 160 following 120 posts
Associate prof at Massey University. Interested in statistics, open science, meta-psychology, and conspiracy theories. https://mattwilliams.netlify.app/
Posts Replies Media Videos
Reposted by Matt Williams
perfors.net
Getting nervous for the talk I'm about to give at a workshop about "using AI to drive impact" which features slides such as these.
Slide is titled: You don't need to use LLMs. Science is a process of collaborative meaning making, by which we try to understand the world Even if AI were perfect, we rely on it at our peril — it is not science if we (i.e., humanity as a whole) do not understand and cannot recapitulate all parts of it I very, very rarely use LLMs myself. You can give yourself permission not to. Don’t FOMO yourself into it Conclusion: Don't rely on something you don't understand and can't control If you must use LLMS: 1. Treat them like you would an intern: only use them for things you can easily and thoroughly check 2. Make your process as robust as possible 3. Be aware of your own (human) cognitive biases
November 6, 2025 at 8:41 PM
Reposted by Matt Williams
mdmarques.com
@srhastraea.bsky.social is a humble & busy guy so the aussie will announce his successful #marsden

Unpacking how we choose who to trust for knowledge in complex, contentious issues with the potential for misinformation

@scicomguy.bsky.social @matthewmatix.bsky.social
@rachelprozac.bsky.social
Marsden Fund Awards 2025
Published on 6 Whiringa-ā-rangi November 2025 You can download an Excel spreadsheet of these results here: 2025-Marsden Fund Supplement The definitions of the 8 Marsden Fund panels can be found here...
www.royalsociety.org.nz
November 5, 2025 at 4:21 AM
Reposted by Matt Williams
lakens.bsky.social
Are you interested in thinking about which studies are worth replicating? Then you have 10 articles to dig into in Meta-Psychology, representing a very wide range of viewpoint on this topic, out now: open.lnu.se/index.php/me...
LnuOpen | Meta-Psychology
Original articles
open.lnu.se
October 30, 2025 at 3:43 PM
Reposted by Matt Williams
bsiepe.bsky.social
We built the openESM database:
▶️60 openly available experience sampling datasets (16K+ participants, 740K+ obs.) in one place
▶️Harmonized (meta-)data, fully open-source software
▶️Filter & search all data, simply download via R/Python

Find out more:
🌐 openesmdata.org
📝 doi.org/10.31234/osf...
October 22, 2025 at 7:34 PM
Reposted by Matt Williams
eddieclarke.bsky.social
Extremely pleased to see this work published! Thank you so much to my excellent collaborators @fmsmallfield.bsky.social @scicomguy.bsky.social @srhastraea.bsky.social @lingtax.bsky.social @mdmarques.com @matthewmatix.bsky.social
onlinelibrary.wiley.com/doi/10.1111/...
Extremism at the center: Uncovering political diversity among midpoint responders on the left–right self‐placement item
The midpoint of the left-right self-placement item is hiding important political diversity, and may be conflating moderate responders with populists and other political sub-groups. Survey researchers...
onlinelibrary.wiley.com
October 23, 2025 at 8:38 AM
Reposted by Matt Williams
dsbarra.bsky.social
Papers from July to Sept 2025 at AMPPS are killer. We don't have formal print issues, but we have this-- journals.sagepub.com/toc/ampa/8/3
Advances in Methods and Practices in Psychological Science - Volume 8, Number 3
Table of contents for Advances in Methods and Practices in Psychological Science, 8, 3
journals.sagepub.com
October 21, 2025 at 7:11 PM
Reposted by Matt Williams
Separating the whack from the chaff in critiques of decision theory
statmodeling.stat.columbia.edu/2025/10/17/s...
Separating the whack from the chaff in critiques of decision theory | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
October 17, 2025 at 8:38 PM
matthewmatix.bsky.social
The existential threat model suggests stress & anxiety can lead to belief in conspiracy theories. And prior studies have showed they are *correlated* with belief in CTs.

But do they *cause* belief in CTs? Find the answer here...

(Or apply Betteridge's law of headlines, if you're pressed for time)
October 17, 2025 at 1:30 AM
Reposted by Matt Williams
ianhussey.mmmdata.io
Results of the replication are in!

Chocolate is more desirable than poop:

Cohen's d_rm = 6.20, 95%CI [5.63, 6.78]

N = 486, two single item 1-7 Likert scales of desirability.

w/
@jamiecummins.bsky.social
ianhussey.mmmdata.io Ian Hussey @ianhussey.mmmdata.io · 29d
Make an effect size prediction!

@jamiecummins.bsky.social and I are replicating Balcetis & Dunning's (2010) "chocolate is more desirable than poop" (Cohen's d = 4.52)

Let us known in the replies what effect size you think we'll find. Details of the study in the thread below.
October 14, 2025 at 6:16 PM
Reposted by Matt Williams
socio-steve.bsky.social
I think words are valuable when they describe some things but not others.
socio-steve.bsky.social Stephen Nuñez @socio-steve.bsky.social · 28d
Neoliberalism has several sins but, "super high tariffs" and "nanny state scolding about nutritional value," are not among them.
October 14, 2025 at 4:48 PM
Reposted by Matt Williams
jeremylabrecque.bsky.social
Should statistical software that estimates causal effects also tell you the causal assumptions under which that estimate can be interpreted as causal?

I don't know but my PhD student Maurice Korf has some thoughts (and software) to get the conversation going:

academic.oup.com/ije/article/...
Causal clarity in statistical software
Imagine running a simple regression in any statistical software of choice—but this time, you only get a point estimate of the regression coefficient. There
academic.oup.com
July 29, 2025 at 7:47 AM
Reposted by Matt Williams
psych.peercommunityin.org
PCI Psychology is open for submissions! Did you know that you can easily submit your recommended preprint to any of the 20+ PCI Psych friendly journals? See all friendly journals here: psych.peercommunityin.org/about/pci_fr...
#PsychSciSky #SciPub
October 13, 2025 at 4:40 PM
Reposted by Matt Williams
ianhussey.mmmdata.io
My article "Data is not available upon request" was published in Meta-Psychology. Very happy to see this out!
open.lnu.se/index.php/me...
LnuOpen | Meta-Psychology
open.lnu.se
October 4, 2025 at 12:54 PM
Reposted by Matt Williams
nickfoxnz.bsky.social
Excited for my doctoral research to be published, thanks to the support of @matthewmatix.bsky.social @srhastraea.bsky.social
Do Stress, Depression, and Anxiety Lead to Beliefs in Conspiracy Theories? - Nick D. Fox, Matt N. Williams, Stephen R. Hill, 2025
Previous research has found positive correlations between manifestations of psychological distress, such as anxiety, depression, and stress, and belief in consp...
doi.org
October 12, 2025 at 8:14 PM
matthewmatix.bsky.social
In which the authors of a 2023 Psych Science paper claim that the correlation between two constants is 1
October 10, 2025 at 1:34 AM
matthewmatix.bsky.social
I'm joining the brilliant @jkarl.bsky.social as co-EIC at Europe's Journal of Psychology. ejop.psychopen.eu/index.php/ejop

EJOP is a generalist psych journal, and applies a diamond open access model (no APC). I'd love to see more submissions with rigorous methods & well-calibrated conclusions!
Europe’s Journal of Psychology
Quarterly peer-reviewed open access journal of scientific psychology featuring original studies, research, critical contributions written by and intended for psychologists worldwide.
ejop.psychopen.eu
October 2, 2025 at 9:52 PM
matthewmatix.bsky.social
PhD holder who didn't collect any original data for my thesis checking in 🙋 The world isn't short of data to analyse!

(I did collect data for my Masters... pen-and-paper surveys from primary school kids... back in the olden days!)
dingdingpeng.the100.ci Julia M. Rohrer @dingdingpeng.the100.ci · Oct 1
A lot of psych is already conducted with online convenience samples & ppl are probably excited about silicon samples bc it would allow them to crank out more studies for even less 💸

How about we reconsider the idea that sciencey science involves collecting own data.
www.science.org/content/arti...
AI-generated ‘participants’ can lead social science experiments astray, study finds
Data produced by “silicon samples” depends on researchers’ exact choice of models, prompts, and settings
www.science.org
October 1, 2025 at 9:47 PM
Reposted by Matt Williams
ianhussey.mmmdata.io
Some researchers don't discuss their future research plans for fear of being scooped.

Not me. I drop bad ideas for unscrupulous people to 'steal'.

- What are the neural correlates of Open Science practices?
- What is the role of habits in learning a new skill through repetitive practice?
a man in a leather jacket is looking up and saying `` big brain '' while standing in front of a building .
ALT: a man in a leather jacket is looking up and saying `` big brain '' while standing in front of a building .
media.tenor.com
September 23, 2025 at 11:48 PM
Reposted by Matt Williams
conradhackett.bsky.social
BEWARE: Surveys that allow anyone to "opt in" are vulnerable to those who create many accounts (using VPN to bypass IP limits) & use automated tools to generate bogus responses (such as saying "yes" to question about being licensed to operate nuclear submarines).
www.pewresearch.org/short-reads/...
September 22, 2025 at 1:36 PM
Reposted by Matt Williams
sophieehill.bsky.social
"Sweeteners can harm cognitive health equivalent to 1.6 years of ageing, study finds"

Or does it? Let's take a look at this "study"...

www.theguardian.com/food/2025/se...
Sweeteners can harm cognitive health equivalent to 1.6 years of ageing, study finds
Researchers say low- and no-calorie sweeteners appear to affect thinking and memory in middle age
www.theguardian.com
September 5, 2025 at 4:46 PM
Reposted by Matt Williams
improvingpsych.org
PsyArXiv's amazing team of 100+ moderators has now approved all preprints that meet the requirements outlined in the updated PsyArXiv policies (is.gd/paxpolicy). Thank you to everyone who volunteered, this was a true community effort! #PsychSciSky
About PsyArXiv – PsyArXiv Blog
What is PsyArXiv? PsyArXiv (psychology archive) is an open preprint archive designed to facilitate rapid dissemination of psychological research. PsyArXiv is a creation of the Society for the…
is.gd
September 11, 2025 at 6:29 PM
matthewmatix.bsky.social
If you have submitted a preprint to PsyArXiv in the last year or so and it *isn't* currently accessible, there's a good chance it's due to the document listing authors whom you haven't entered in the metadata.
September 11, 2025 at 8:42 AM
Reposted by Matt Williams
lhuntneuro.bsky.social
Great list for all kinds of claims, not just autism.
wiringthebrain.bsky.social Kevin Mitchell @wiringthebrain.bsky.social · Sep 7
When reporting on these kinds of claims, the media should ask:
1. Is this a one-off study or a replicated finding? 2. Is it cherry-picked or consistent? 3. Was the study big enough to be reliable? 4. Did it employ robust statistical methods? 5. How big is the effect size? (If there’s a statistical association, does it amount to a big risk or a small one?) 6. Is there any evidence for a causal link or is it just a correlation? 7. Could the correlation reflect some confounding factor? 8. How does this supposed factor sit in the context of other factors (especially genetic risk for autism, which is very highly heritable)?
September 7, 2025 at 8:02 PM
Reposted by Matt Williams
improvingpsych.org
PsyArXiv is now down to only ~40% of the backlog we started with, thanks to our amazing moderators 🎉 To all mods: thank you so much for your hard work!

Did one of your preprints get approved recently? Help us show our thanks by liking and sharing this post :)

#PsyArXiv #PsychSciSky
August 30, 2025 at 10:02 PM
Reposted by Matt Williams
aimosinc.bsky.social
Submissions for #AIMOS2025 in Sydney close in just under two weeks!
aimos-inc.github.io/aimos.confer...
August 19, 2025 at 12:34 AM