Ian Hussey
@ianhussey.mmmdata.io
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. If behaviorism did not exist, it would be necessary to invent it.
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}?"
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}?"
Reposted by Ian Hussey
This is good. Authors ask an LLM to write a systematic review. The LLM states ‘prospectively registered’ and includes a fake registration number. When queried, authors send a corrected reg number…which has been created after the query. You love to see it. Happy new year!
January 13, 2026 at 4:50 PM
This is good. Authors ask an LLM to write a systematic review. The LLM states ‘prospectively registered’ and includes a fake registration number. When queried, authors send a corrected reg number…which has been created after the query. You love to see it. Happy new year!
Reposted by Ian Hussey
Tomorrow I’ll be speaking on a panel for the WHO webinar Social Health and Digital Play: A Conversation, Not a Conclusion. I’ll be sharing insights from a recent Delphi study focusing on priorities and future directions in video game research.
If this topic is of interest, feel free to join!
If this topic is of interest, feel free to join!
Social Health and Digital Play: A Conversation, Not a Conclusion
Join us for a public webinar on Social Health and Digital Play: A Conversation, Not a Conclusion where we aim to share insights from WHO’s work on social connection; reflect on the current state of th...
www.who.int
January 13, 2026 at 2:31 PM
Tomorrow I’ll be speaking on a panel for the WHO webinar Social Health and Digital Play: A Conversation, Not a Conclusion. I’ll be sharing insights from a recent Delphi study focusing on priorities and future directions in video game research.
If this topic is of interest, feel free to join!
If this topic is of interest, feel free to join!
Reposted by Ian Hussey
Left as an exercise to the reader
January 13, 2026 at 7:51 AM
Left as an exercise to the reader
There’s nothing about those publications to brag about
January 12, 2026 at 8:40 PM
There’s nothing about those publications to brag about
Is it a bad time to tell you I had 12 publications upon graduation? That lab was trained in 🔪🥓
January 12, 2026 at 8:14 PM
Is it a bad time to tell you I had 12 publications upon graduation? That lab was trained in 🔪🥓
One thing to bear in mind is that people can postdoc here for a much longer time from what I know of the US, and this changes what the role is imo. There are even small numbers of tenured postdoc positions. There are many highly technical 7th+ year postdocs around.
January 12, 2026 at 7:54 PM
One thing to bear in mind is that people can postdoc here for a much longer time from what I know of the US, and this changes what the role is imo. There are even small numbers of tenured postdoc positions. There are many highly technical 7th+ year postdocs around.
Seconded for OS, and not even as a virtue: many PIs have OS expectations or requirements on them that they might not have the skills to fulfill alone, and rely on postdocs to drive forward.
January 12, 2026 at 7:51 PM
Seconded for OS, and not even as a virtue: many PIs have OS expectations or requirements on them that they might not have the skills to fulfill alone, and rely on postdocs to drive forward.
I presume you mean that 5+ would raise eyebrows in a good way?
I think technical skills are in high demand, from what I see around Belgium/NL/German/Switzerland.
I think technical skills are in high demand, from what I see around Belgium/NL/German/Switzerland.
January 12, 2026 at 7:49 PM
I presume you mean that 5+ would raise eyebrows in a good way?
I think technical skills are in high demand, from what I see around Belgium/NL/German/Switzerland.
I think technical skills are in high demand, from what I see around Belgium/NL/German/Switzerland.
Reposted by Ian Hussey
hey European hivemind, I need some help...PhD students here, especially foreign ones, are feeling a lot of concern related to evolving immigration restrictions here. Those students are increasingly looking to postdocs in EU. To help advise them better, what are expectations for postdocs?
1/2
1/2
January 12, 2026 at 6:37 PM
hey European hivemind, I need some help...PhD students here, especially foreign ones, are feeling a lot of concern related to evolving immigration restrictions here. Those students are increasingly looking to postdocs in EU. To help advise them better, what are expectations for postdocs?
1/2
1/2
Me: surely at least the statistics literature has its house in order.
The stats literature:
The stats literature:
January 12, 2026 at 2:58 PM
Me: surely at least the statistics literature has its house in order.
The stats literature:
The stats literature:
Reposted by Ian Hussey
So here is one about the GRIM test, or granularity-related inconsistency of means: e.g., 20 integer data points can't have a mean of 4.39, but 100 data points can. In other words, the Ns justify the means.
January 12, 2026 at 12:58 PM
So here is one about the GRIM test, or granularity-related inconsistency of means: e.g., 20 integer data points can't have a mean of 4.39, but 100 data points can. In other words, the Ns justify the means.
Reposted by Ian Hussey
🔍 Sleuthing challenge 🔍
How many suspicious patterns can you find in this table?
(You don't need to know what the variables are.)
Hints in next post! 👇
How many suspicious patterns can you find in this table?
(You don't need to know what the variables are.)
Hints in next post! 👇
January 11, 2026 at 6:14 AM
🔍 Sleuthing challenge 🔍
How many suspicious patterns can you find in this table?
(You don't need to know what the variables are.)
Hints in next post! 👇
How many suspicious patterns can you find in this table?
(You don't need to know what the variables are.)
Hints in next post! 👇
Standards are nowhere near as universal as the cohen ones. The {effectsize} R package collects and implements guidelines for interpretation, it’s a good go-to for a standard with references. I don’t know if my comment is in compliance with it. But the effect sizes are substantively very large.
January 9, 2026 at 12:49 PM
Standards are nowhere near as universal as the cohen ones. The {effectsize} R package collects and implements guidelines for interpretation, it’s a good go-to for a standard with references. I don’t know if my comment is in compliance with it. But the effect sizes are substantively very large.
More than 18 months have passed since I contacted the authors of this meta-analysis about serious flaws that substantially change the results.
More than 6 have passed since the published was involved.
No action taken.
One of the component studies has since been retracted.
More than 6 have passed since the published was involved.
No action taken.
One of the component studies has since been retracted.
PubPeer - Effect of acceptance and commitment therapy for depressive d...
There are comments on PubPeer for publication: Effect of acceptance and commitment therapy for depressive disorders: a meta-analysis (2023)
pubpeer.com
January 9, 2026 at 11:34 AM
More than 18 months have passed since I contacted the authors of this meta-analysis about serious flaws that substantially change the results.
More than 6 have passed since the published was involved.
No action taken.
One of the component studies has since been retracted.
More than 6 have passed since the published was involved.
No action taken.
One of the component studies has since been retracted.
There are discrepancies between Table 3 and Table 4.
If you recalculate from Table 3, the primary outcome is Cohen's d = 21 (!)
pubpeer.com/publications...
If you recalculate from Table 3, the primary outcome is Cohen's d = 21 (!)
pubpeer.com/publications...
January 9, 2026 at 10:12 AM
There are discrepancies between Table 3 and Table 4.
If you recalculate from Table 3, the primary outcome is Cohen's d = 21 (!)
pubpeer.com/publications...
If you recalculate from Table 3, the primary outcome is Cohen's d = 21 (!)
pubpeer.com/publications...
Seems like they have a mix of SDs and SEs
January 9, 2026 at 7:20 AM
Seems like they have a mix of SDs and SEs
Reposted by Ian Hussey
AI presents a fundamental threat to our ability to use polls to assess public opinion. Bad actors who are able to infiltrate panels can flip close election polls for less than the cost of a Starbucks coffee. Models will also infer and confirm hypotheses in experiments. Current quality checks fail
November 18, 2025 at 9:23 PM
AI presents a fundamental threat to our ability to use polls to assess public opinion. Bad actors who are able to infiltrate panels can flip close election polls for less than the cost of a Starbucks coffee. Models will also infer and confirm hypotheses in experiments. Current quality checks fail
Reposted by Ian Hussey
“These findings provide clear evidence that data collected on MTurk simply cannot be trusted.”
January 8, 2026 at 8:47 PM
“These findings provide clear evidence that data collected on MTurk simply cannot be trusted.”
Perhaps there are other inconsistencies - I only looked at PSS at post.
January 8, 2026 at 9:23 PM
Perhaps there are other inconsistencies - I only looked at PSS at post.
My calculator takes rounding into account and lets you explore if SE has been confused for SE - I think that’s likely here. It still comes out as d = 3.7 if you assume they are SEs though.
errors.shinyapps.io/recalc_indep...
errors.shinyapps.io/recalc_indep...
recalc: Bounds of an independent t-test's p-value and Cohen's d from M/SD/N
errors.shinyapps.io
January 8, 2026 at 9:23 PM
My calculator takes rounding into account and lets you explore if SE has been confused for SE - I think that’s likely here. It still comes out as d = 3.7 if you assume they are SEs though.
errors.shinyapps.io/recalc_indep...
errors.shinyapps.io/recalc_indep...
Seems like there are inconsistencies in the summary stats repeated between Table 3 and Table 4. I think you’ve used those from table 4. When I use those from table 3 I get cohens d of about 21 (!)
recalc: Bounds of an independent t-test's p-value and Cohen's d from M/SD/N
errors.shinyapps.io
January 8, 2026 at 9:23 PM
Seems like there are inconsistencies in the summary stats repeated between Table 3 and Table 4. I think you’ve used those from table 4. When I use those from table 3 I get cohens d of about 21 (!)
Reposted by Ian Hussey
First MEP report.
Medical research often uses non-parametric tests. We looked, and noticed that small-sample rank-based tests (i.e. M-W, Wilcoxon) have significant granularity... like p-values!
So, here's GRIM for U values -- GRIM-U.
Enjoy.
medicalevidenceproject.org/grim-u-obser...
Medical research often uses non-parametric tests. We looked, and noticed that small-sample rank-based tests (i.e. M-W, Wilcoxon) have significant granularity... like p-values!
So, here's GRIM for U values -- GRIM-U.
Enjoy.
medicalevidenceproject.org/grim-u-obser...
GRIM-U: A GRIM-like observation to establish impossible p values from ranked tests - Medical Evidence Project
The Medical Evidence Project uses forensic metascientific methods to examine medical research publications that have a disproportionately high impact on human health. Our aim is to determine where pro...
https://medicalevidenceproject.org/grim-u-observation-establish-impossible-p-values-ranked-tests/"
January 7, 2026 at 2:53 PM
First MEP report.
Medical research often uses non-parametric tests. We looked, and noticed that small-sample rank-based tests (i.e. M-W, Wilcoxon) have significant granularity... like p-values!
So, here's GRIM for U values -- GRIM-U.
Enjoy.
medicalevidenceproject.org/grim-u-obser...
Medical research often uses non-parametric tests. We looked, and noticed that small-sample rank-based tests (i.e. M-W, Wilcoxon) have significant granularity... like p-values!
So, here's GRIM for U values -- GRIM-U.
Enjoy.
medicalevidenceproject.org/grim-u-obser...