Ian Hussey

@ianhussey.mmmdata.io

3.2K followers 870 following 810 posts

Meta-scientist and psychologist. Senior lecturer @unibe.ch‬. Chief recommender @error.reviews. "Jumped up punk who hasn't earned his stripes." All views a product of my learning history.

Videos

Psychology 66%

Sociology 10%

Posts Replies Media Videos

Pinned

Ian Hussey @ianhussey.mmmdata.io · Jul 22

Lego Science is research driven by modular convenience.

When researchers combine methods or concepts, more out of convenience than any deep curiosity in the resulting research question, to create publishable units.

"What role does {my favourite construct} play in {task}?"

Ian Hussey @ianhussey.mmmdata.io · 1d

None of this is incompatible with my statement. Are you arguing for a lack of caution? Strange position to take in science.

Ian Hussey @ianhussey.mmmdata.io · 1d

I think once we find out that someone has fabricated much of their work, we should be very careful to treat the remainder of their work as trustworthy.

Reposted by Ian Hussey

Josh Grubbs @joshuagrubbsphd.bsky.social · 3d

Anyone check in on Johnny Haidt to see if he thinks Bari Weiss still embodies the “telos of truth”

Ian Hussey @ianhussey.mmmdata.io · 5d

Your last saved meme is your moral philosophy

Reposted by Ian Hussey

Michel Nivard @michelnivard.bsky.social · 6d

🚨🚨 ATTENTION: I’d like to announce that I, unilaterally but bindingly, have changed the name from “Spearman’s rho” to “Nivard-Spearman’s rho”. I’ll be in talks with package and software maintainers to organize a smooth transfer to the new, more appropriate, terminology.

Reposted by Ian Hussey

Malte Elson @malte.the100.ci · 7d

I regularly cite Prinz et al.(www.nature.com/articles/nrd...) as a ref for low replicability in (non-psych) preclinical research. Believe it or not: They've omitted which studies they attempted to replicate!

I'm guessing this isn't news to everyone, but it was to me. Bizarre.

Believe it or not: how much can we rely on published data on potential drug targets? - Nature Reviews Drug Discovery

Nature Reviews Drug Discovery - Believe it or not: how much can we rely on published data on potential drug targets?

www.nature.com

Ian Hussey @ianhussey.mmmdata.io · 7d

I’ll send one in future 😉

Reposted by Alexander Wuttke

Ian Hussey @ianhussey.mmmdata.io · 7d

I’m vocally skeptical of silicon samples, yet vocally impressed by SurveyBot3000.

The difference: this does not rely on magic beans or assumed omniscience, it is trained and validated against a large corpus of highly relevant data and makes specific predictions with known accuracy and precision.

Ruben C. Arslan @ruben.the100.ci · 7d

Finally, @bjoernhommel.bsky.social's and my paper introducing the SurveyBot3000 is officially out in AMPPS. It's a fine-tuned language model that guesstimates correlations between survey items from text alone. Not perfectly, but useful for search, for example.
journals.sagepub.com/doi/10.1177/...

Fig. 3. Scatter plots of the synthetic and empirical estimates, validation study (Stage 2). Showing N = 30,135 item-pair correlations, N = 257 scale reliabilities, and N = 1,568 scale-pair correlations for (top) the pretrained SBERT model and (bottom) the fine-tuned SurveyBot3000 model. SBERT = all-mpnet-base-v2 model.

Fig. 4. Prediction error of the synthetic estimates, validation study (Stage 2). Our prediction model allowed the error term to vary freely according to the predictor, the synthetic estimate. The thin-plate splines show that some synthetic estimates were predictably more accurate.

Fig. 5. Accuracy by domain. Accuracy differed across domains. SurveyBot3000 accuracy (colored) was always higher than SBERT accuracy (gray). Results were largely consistent whether accuracy of items was tested (left, circle) within domains or (right, cross) across domains.

Fig. 1. Multistep training procedure for the SurveyBot3000, which produces synthetic estimates of interitem correlations. (a) Pretraining base model (SBERT). (b) Fine-tuning SurveyBot3000. (c) Validation. SBERT = all-mpnet-base-v2 model.

Reposted by Alexander Wuttke, Cameron Brick, Ian Hussey , and 3 more Alexander Wuttke, Cameron Brick, Ian Hussey, Eric Hehman, Jana Lasser, Johannes Breuer

Ruben C. Arslan @ruben.the100.ci · 7d

Ian Hussey @ianhussey.mmmdata.io · 7d

The fact that you have written about thus seriously elsewhere makes it more likely that this piece is taken seriously. That makes it worse, not better. How is the reader to know to read it as if you have your fingers crossed while writing it?

Reposted by Alberto Acerbi

Ian Hussey @ianhussey.mmmdata.io · 7d

Author of “How the phone ban saved high school" clarifies that the article is not meant to imply that the phone ban has saved high school.

There is no way this could cause confusion in this heated space.
¯\_(ツ)_/¯

Reposted by Juan Ramón

Ian Hussey @ianhussey.mmmdata.io · 8d

Oliver Sacks admitted his case studies in The Man Who Mistook His Wife For A Hat were fraudulent “fairy tales”.

What Psych101 core texts are left?

www.newyorker.com/magazine/202...

Reposted by Ian Hussey

Swiss National Science Foundation (SNSF) @snsf.ch · 8d

The SNSF is considering restrictions for its Project funding. Goal: to ensure the quality of evaluation & stable success rates despite an increasing number of applications and limited funding. The final decision will be made in January 2026.

👉 buff.ly/iGOCf7R

#research #science

Project funding restrictions envisaged

The SNSF is responding to increased demand from researchers in order to ensure evaluation quality and stabilise success rates.

buff.ly

Reposted by Ian Hussey, Juan Rocha

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 8d

I am just learning of this 2015 retraction, adding to my "science as amateur software engineering" files. Seems they classified missing values as obs outcome of interest (divorce). Classified 32% of sample divorced, rather than true 5%. retractionwatch.com/2015/07/21/t...

Here’s the original coding line:

replace event`i’ = 1 if delta_mct`i’ != 0 | spouse_delta_mct`i’ != 0

And here’s the corrected coding:

replace event`i’ = 1 if (delta_mct`i’ != 0 | spouse_delta_mct`i’ != 0) & delta_mct`i’ != . & spouse_delta_mct`i’ != .

Reposted by Ian Hussey

Malte Elson @malte.the100.ci · 8d

While we are unable to offer publication in Nature Aging, we believe your manuscript may be suitable for our Gold Open Access sister journal.

Ian Hussey @ianhussey.mmmdata.io · 8d

I wish we could publish graphical abstracts with no article, and therefore make memes like this citable objects.

Reposted by Ian Hussey

Eiko Fried @eikofried.bsky.social · 9d

Thanks @janhove.bsky.social for taking the time to check the paper — something that paid editors at Nature, as well as unpaid reviewers — apparently did not.

Also shows once more that providing statistical code should be mandatory for every single paper.

janhove.github.io/posts/2025-1...

Jan Vanhove :: Blog - Does multilingualism really protect against accelerated ageing? Some critical comments

janhove.github.io

Ian Hussey @ianhussey.mmmdata.io · 9d

This was a contentious debate in suicide research. I couldn’t convince several people it was the case.

Reposted by Brian A. Nosek, Ian Hussey

Sholto David @sholtodavid.bsky.social · 9d

Dana-Farber Cancer Institute Agrees to Pay $15 Million to Settle Fraud Allegations Related to Scientific Research Grants. The relator [Sholto David] will receive $2,625,000 under today’s settlement.
www.justice.gov/usao-ma/pr/d...

Dana-Farber Cancer Institute Agrees to Pay $15 Million to Settle Fraud Allegations Related to Scientific Research Grants

BOSTON – Dana-Farber Cancer Institute, Inc. (Dana-Farber) has agreed to pay $15 million to resolve allegations that, between 2014 and 2024, it made materially false statements and certifications relat...

www.justice.gov

Ian Hussey @ianhussey.mmmdata.io · 9d

already happening in similar forms by big name folk bsky.app/profile/ianh...

Ian Hussey @ianhussey.mmmdata.io · 16d

Many psychologists are treating LLMs as if they are the mind of god.

This study had chatGPT rate how central academic disciplines are to various constructs.

Why would chatGPT know this?

Where is the evidence its ratings are reliable or valid?

compass.onlinelibrary.wiley.com/doi/full/10....

Ian Hussey @ianhussey.mmmdata.io · 9d

Needs hallucinated emojis in 1% of cases

Ian Hussey @ianhussey.mmmdata.io · 9d

Their site says it has been trained on “thousands” of human participants.. which seems very low for such a product?

Ian Hussey @ianhussey.mmmdata.io · 9d

This is news to me.

My fear is: will everyone 'collecting' silicon samples on Qualtrics realise that they have not collected data from real participants? Will some people not realise they have done 'ask-chatgpt-if-my-hypothesis-is-right' with extra steps?

Sabrina Norwood @sabrinanorwood.bsky.social · 9d

Did you know that from tomorrow, Qualtrics is offering synthetic panels (AI-generated participants)?

Follow me down a rabbit hole I'm calling "doing science is tough and I'm so busy, can't we just make up participants?"

Text reads: About synthetic panels
Recruiting the right participants for a study can be difficult. You may not get the exact demographics you need, and the shorter the deadline, the less sure you can be that everyone will answer on time. One possible solution can be to use synthetic panels.

Synthetic panels are powered by a first party proprietary AI model developed here at Qualtrics. Our synthetic panel is trained on thousands of responses from a variety of demographic backgrounds in order to more accurately predict how certain populations would respond to a survey.

Our synthetic panel is based on the United States General Population, and is only available in English. This panel comes with ready-made quotas and target breakouts in order to represent your chosen population and make it easy to launch your survey right away.

Text reads:
Discussion
The current study aimed to conduct a meta-analysis of the TPB when applied to health behaviours which addressed the limitations of previous reviews by including only prospective tests of behaviour, applying RE meta-analytic procedures, correcting correlations for sampling and measurement error, and hierarchically analysing the effect of behaviour type and sample and methodological moderators. Some 237 tests were identified which examined relations amongst model components. Overall the analysis indicated that the TPB could explain 19.3% of the variance in behaviour and 44.3% of the variance in intention across studies. This level of prediction of behaviour is slightly lower than that of previous meta-analytic reviews which have found between 27% (Armitage & Conner, 2001; Hagger et al., 2002) and 36% (Trafimow et al., 2002)
of the variance in behaviour to be explained by intention and PBC.

Reposted by Robert Böhm, Brady T. West, Brendan Nyhan , and 43 more Robert Böhm, Brady T. West, Brendan Nyhan, Gordon Hodson, Carl T. Bergstrom, Richard Price, Steven Van de Walle, Mary Feeney, Jamie Morgan, Ian Hall, Fabián Muniesa, Jason Reifler, Kelly Smith, Ingo Rohlfing, Ian Hussey, James Grimmelmann, Smith, Rebecca Tushnet, David R. Miller, Patrick S. Forscher, Michelle L. Mazurek, Margot C. Finn, Michael D. McDonald, Sebastian Karcher, Martin Kreidl, Maria Abreu, Eric Hehman, Zen Faulkes, Joanna Tai, Madeleine Pownall, Damian Trilling, David Murakami Wood, Sofia Stathi, Johannes Breuer, Woodrow Hartzog, Greg Linden, Jack Stilgoe, Richard M. Carpiano, Aleksandra Urman, Juan Ramón, Gemma C. Sharp, Terry Gaasterland, Maksym Polyakov, Jake Anders, Jeannette Sutton, Béatrice Cointe

Sabrina Norwood @sabrinanorwood.bsky.social · 9d

Ian Hussey @ianhussey.mmmdata.io · 9d

If you read the post, you’ll see these questions are answered there.

Ian Hussey @ianhussey.mmmdata.io · 9d

These authors are not a priori at fault, but they represent a useful lead for examining that work further from a forensic scientiometrics perspective.

Ian Hussey @ianhussey.mmmdata.io · 9d

I think you miss the point. It is obvious that researchers cite themselves. So it is therefore not obvious why an established researcher would never ever cite themselves in any of their articles. That’s what the 2% represents.

Ian Hussey @ianhussey.mmmdata.io · 10d

Only about 2% of researchers have never cited their own work.

Most of us are aware of inappropriately high rates of self-citation. I had never considered the opposite: that exceptionally low levels of self-citation could indicate papermill activity.

fosci.substack.com/p/self-citat...

Self-citation patterns among researchers

What's normal? What's unusual?

fosci.substack.com

Reposted by Ian Hussey, Paolo Crosetto

Jan Vanhove @janhove.bsky.social · 10d

A recent study purports to have found that multilingualism protects against accelerated ageing. I've taken a closer look at it, and it doesn't look good.

New blog post: "Does multilingualism really protect against accelerated ageing? Some critical comments"
janhove.github.io/posts/2025-1...

Positive trend between monolingualism and accelerated ageing.

Negative trend between per capita GDP and accelerated ageing.

Ian Hussey @ianhussey.mmmdata.io · 11d

I don't care what it did to our political landscape, that sounds delicious. Worth it.

Add to Home Screen

Light up
your news

Add to Home Screen

Light upyour news

Sign in to Lightnews

Sign up to start reading

Connect Bluesky

Connect with Bluesky

Light up
your news