@markrubin
social psychology ▪︎ metascience ▪︎ philosophy of science ▪︎ higher education Professor at Durham University, UK. He/him. Website: https://sites.google.com/site/markrubinsocialpsychresearch/ Substack: https://markrubin.substack.com/
THAMES Time, MFers!!
Episode 3 of the blog series, all about the SIX SECRET LETTERS FOR CRITICAL THINKING THAT THE SCIENTISTS DONT WANT YOU TO KNOW
willgervais.com/blog/2026/3/...
#psychscisky 🧪 #philsci #methodology #teaching
📃 Call for Papers 📃
“Current and New Directions in Cross-Cultural Gender Research in Psychology”
Abstracts due: 01 May 2026
#SocialPsyc #AcademicSky #PhDSky
Citizens tend to lose faith in meritocracy as inequality rises within their country over time.
#SocialPsyc
Hadn't seen it before today - it's great!
Not a fan of terms like "stabilize" for this purpose. To me that conjures up an image of something more dynamic/mechanistic than what is going on. Stable as opposed to chaotic. Not just diminishing returns from additional N. #stats
Trying a new thing in 2024. I have a lot (!) of stats related tabs open. I never get around to sorting which are useful. So, I will crowdsource my neurosis. I'll (try to) post one link per day and ask blue-sky #stats for your thoughts. First one of #statstab below:
Yes really interesting stuff that aligns well with my own views! And congrats on #statstab 500! 🎉 Very helpful educational service to the community 👏
Looking forward to #statstab 1000 sometime in 2028!
Vice Chancellor Prof Andy Long explained that:
“Northumbria is not facing the kind of existential crisis affecting some institutions in our sector. We are acting now precisely because we are in a position of relative strength, and we intend to stay there.”
#UKHE
“UCU regional official Lawson Armstrong pointed out that the £25 million savings target is the same amount the university is spending on the building of a space skills, research and development centre.”
Staff at Northumbria University told the uni needs to save £25 million by the end of the year. Voluntary severance is now on offer.
Yes parapsychology has a lot to teach us.
But I'd say, to have repeatable observations you need at least an interpretative theory, otherwise you don't know what you're observing and whether it's been "repeated."
#PhilSci #Methodology
Naive empiricism and methodologism
"The dogged experimental pursuit of paraphysical results within a vacuum of genuine paraphysical theory seems to me to be methodologically barren, even if the experiments are performed with meticulous care, and even if they produce some genuinely puzzling results"
If someone predicts the results of a long series of coin tosses with 100 percent accuracy, it is no explanation of this surprising result simply to say that the subject "has precognition." As well explain why sodium amy tal puts you to sleep ,by saying it "has a dormative virtue." A real explanation would cite the nonphysical mechanisms involved, identify the empirical facts that reflect them, appeal to the laws that govern them, and then deduce exactly the surprising effect observed. Parapsychology does none of these things.
"If someone predicts the results of a long series of coin tosses with 100 percent
accuracy, it is no explanation of this surprising result simply to say that
the subject 'has precognition'."
There are further problems with the methodology of looking for some effect, any effect, that cannot be accounted for in normal physical terms. For when such results are achieved (or rather, are alleged to be achieved), the results may indeed be mysterious from a physical point of view, but they remain equally mysterious from the nonphysical point of view. The reason is that the parapsychologists are no better able to provide an explanation than are the physicists, for parapsychology has no significant theoretical resources with which to construct any explanations.
Theories are needed to explain effects...
And when we move to a new theoretical framework...
"Such a reconfigured vision can reveal dramatic failures in the old theory, failures that were invisible, as failures, from within the old framework."
It remains possible, however, that the important empirical facts that reflect the falsehood of the favored and so far "successful" theory are to be found in precisely those experimental areas thought to be intractable, or are to be found just over the horizon of controlled detail in areas that are tractable. In such cases the favored theory enjoys a safety from refutation that it does not deserve. The refuting facts are there, but for complex reasons they are difficult or impossible to see, at least while we continue to interpret the situation in terms of the favored theory. For it is that same theory that helps us decide which details are relevant and which are irrelevant, and which situations are tractable and which are intractable.
"The refuting facts are there, but for complex reasons they are difficult or impossible to see, at least while we continue to interpret the situation in terms of the favored theory."
"There is no essential vice in this. The alternative is to try to control the position and character of every particle in the universe. Instead, we control as much as we think it is necessary and prudent to control, and let the rest go."
"Any successful theory quite properly ignores or suppresses a good deal of faintly troublesome empirical evidence as irrelevant and inevitable 'noise'."
"Pulling new signal out of old noise."
Fascinating discussion of the importance of theory and theory change in science, and not just parapsychology... 🧵
#statstab #499 SIMPLICITY AND COMPLEXITY IN ECOLOGICAL DATA ANALYSIS
Thoughts: I dislike this paper, but I don't mind sharing views that disagree with my own. Effective communication matters.
#analysis #critique #critical #ANOVA #ttest #simplicity #communication
doi.org/10.1890/0012...
Parsimony Since all models are wrong the scientist cannot obtain a "correct" one by excessive elaboration. On the contrary following William of Occam he should seek an economical description of natural phenomena. Just as the ability to devise simple but evocative models is the signature of the great scientist so overelaboration and overparameterization is often the mark of mediocrity.
Fair enough. Yes simpler ≠ better. But also better ≠ complex, and I sometimes worry that people use fancy stats to impress rather than out of necessity.
Anyway, here’s Box (1976) on parsimony: doi.org/10.1080/0162... And looking forward to your post!
Appreciate you sharing. Why don't you like it?
(Working link:
doi.org/10.1890/0012... )
Maybe one for the platform's founder @mfenner.bsky.social to check out.
VERY excited for this event as part of the London Open Science & Scholarship Festival 2026 (online, April 20th).
We don’t talk enough about the patriarchal ideologies embedded in many dominant applications of “open science “
For similar results, see...
#MetaSci #SocialPsyc
Whereas our findings support a moderate effect of MS on clinically relevant symptoms, several limitations temper the strength of these conclusions. The observed heterogeneity, combined with flexible outcome operationalizations and the near-total absence of manipulation checks highlight the need for greater critical scrutiny. Although p-curve analyses suggest evidential value, z-curve results point to low replicability and inflated discovery rates, raising concerns about the stability of the MS effects. This reinforces the fact that relying solely on traditional univariate meta-analytic approaches may no longer be sufficient on their own. Instead, we propose a shift toward more transparent, multi-method evaluations integrating a balanced perspective on both the strengths and blind spots of (TMT) research.
“We propose a shift toward more transparent, multi-method evaluations integrating a balanced perspective on both the strengths and blind spots of (TMT) [terror management theory] research.”
![Terror Management Theory (TMT) proposes that awareness of one’s mortality can trigger emotional distress and amplify symptoms in vulnerable individuals when protective buffers are weakened. However, doubts about replicability and methodological rigor have grown. We conducted a multivariate three-level meta-analysis examining mortality salience effects on clinically relevant outcomes, synthesizing 61 outcomes from 22 randomized controlled trials (N = 2571). Results showed a moderate pooled effect (g = 0.49, 95% CI [0.20, 0.79]), with significant moderation by DSM-5 symptom type, delay presence, and study location. Publication bias was evaluated using multilevel Egger’s tests, the three-parameter selection model, and both p-curve and z-curve. P-curve indicated evidential value and moderate-to-high power, whereas z-curve suggested inflated discovery rates and low replicability. Overall, findings point to the need for stronger transparency and methodological checks, whereas the substantial heterogeneity in outcome measures and considerable flexibility in interpretation raise concerns about the robustness of TMT research.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:4jb3re5tvklsvhuc3lkerj5q/bafkreibtdr35svmux22o2ywolspiwqmsmwi6ykoihi56r4ajqxgpwubd4q)
Terror Management Theory (TMT) proposes that awareness of one’s mortality can trigger emotional distress and amplify symptoms in vulnerable individuals when protective buffers are weakened. However, doubts about replicability and methodological rigor have grown. We conducted a multivariate three-level meta-analysis examining mortality salience effects on clinically relevant outcomes, synthesizing 61 outcomes from 22 randomized controlled trials (N = 2571). Results showed a moderate pooled effect (g = 0.49, 95% CI [0.20, 0.79]), with significant moderation by DSM-5 symptom type, delay presence, and study location. Publication bias was evaluated using multilevel Egger’s tests, the three-parameter selection model, and both p-curve and z-curve. P-curve indicated evidential value and moderate-to-high power, whereas z-curve suggested inflated discovery rates and low replicability. Overall, findings point to the need for stronger transparency and methodological checks, whereas the substantial heterogeneity in outcome measures and considerable flexibility in interpretation raise concerns about the robustness of TMT research.
New meta-analysis finds “that MS [mortality salience] effects on clinically relevant outcomes may exist, yet remain fragile and difficult to reproduce consistently.”
www.tandfonline.com/doi/full/10....
Recently published...
The Oxford Handbook of Leadership, Followership, and Identity
doi.org/10.1093/oxfo...
#SocialPsyc #OrgPsyc
#SocialPsyc #MetaSci