#Meta-Analyses
LightNews LightNews
brendannyhan.bsky.social
"after the company's own analyses found that these classifiers could reduce the reach of these hoaxes by more than 90 percent, Meta is shutting them off"
caseynewton.bsky.social Casey Newton @caseynewton.bsky.social · Jan 15
NEW: Meta has quietly dismantled the system that prevented misinformation from spreading in the United States. Machine-learning classifiers that once identified viral hoaxes and limited their reach have now been switched off, Platformer has learned www.platformer.news/meta-ends-mi...
Behind the scenes, the company was also quietly dismantling a system to prevent the spread of misinformation. When the company announced on Jan. 7 that it would end its fact-checking partnerships, the company also instructed teams responsible for ranking content in the company’s apps to stop penalizing misinformation, according to sources and an internal document obtained by Platformer. The result is that the sort of viral hoaxes that ran roughshod over the platform during the 2016 US presidential election — “Pope Francis endorses Trump,” Pizzagate, and all the rest — are now just as eligible for free amplification on Facebook, Instagram, and Threads as true stories.
January 15, 2025 at 2:06 AM
matthewbjane.bsky.social
Happy Friday everyone! I just posted what I think is an important blog post on my website. It is a critique of meta-meta-analyses: meta-analyses of meta-analyses.

Link: matthewbjane.github.io/blog-posts/b...

#stats #metascience
May 23, 2025 at 10:47 PM
gavinyamey.bsky.social
Another study finds no link between taking acetaminophen (Tylenol) during pregnancy & autism or ADHD

The study examined data from 7 meta-analyses involving more than 3 million participants

I wish RFK Jr & Trump would stop terrorizing people about this drug

onlinelibrary.wiley.com/doi/10.1111/...
Prenatal exposure to paracetamol and the risk of autism and attention‐deficit/hyperactivity disorder: An umbrella review and meta‐meta‐analysis
This meta-meta-analysis synthesizes evidence on prenatal paracetamol exposure and neurodevelopmental outcomes. Crude analyses suggest small associations with autism and ADHD, but these attenuate subs...
onlinelibrary.wiley.com
September 24, 2026 at 1:48 PM
sailorrooscout.bsky.social
More recently (9/23), an umbrella review, published in Developmental Medicine & Child Neurology, that included data from SEVEN meta-analyses and involved MORE THAN 3 million participants showed Tylenol use during pregnancy was NOT linked to autism nor ADHD.
• www.cidrap.umn.edu/anti-science...
September 25, 2026 at 4:03 PM
daniellebeckman.bsky.social
The kids aren't alright.
#LongCovidKids
Figure from the manuscript: Long-COVID in children and adolescents: a systematic review and meta-analyses. Meta-analyses revealed the prevalence of more than 40 long-COVID symptoms in children and adolescents. The presence of one or more symptoms following a SARS-CoV-2 infection was 25.24%.
November 27, 2024 at 3:33 AM
dsquintana.bsky.social
Sharing the raw data used in meta-analyses should be mandatory in all circumstances
lakens.bsky.social Daniel Lakens @lakens.bsky.social · Jun 3
Max wanted a bit of a provocative talk tomorrow. So I will talk about which open science should become mandatory. For example, science funders now often require open access publication and data sharing. Which open science practices do you think should become mandatory, and under which circumstances?
ditroilo.bsky.social Max Ditroilo @ditroilo.bsky.social · May 13
At University College Dublin we are delighted to host @lakens.bsky.social from Eindhoven University of Technology. On Wed 4th of June, 12-13, C006 Health Sciences, Prof. Lakens will give a talk on open science and will discuss why it is worth improving our research practices. All welcome!
June 3, 2025 at 6:46 AM
matthewbjane.bsky.social
I made a little diagram for illustrating the difference between fixed effects and random effects meta-analyses. #stats
October 3, 2023 at 11:36 PM
anddroiden.bsky.social
It isn't. meta has always been a word that describes a layer above the concrete. A meta analysis is for example an analysis that looks at multiple analyses or surveys.

META is a backronym where people make up an acronym that fits the word.
January 28, 2026 at 12:59 AM
aljazeera.com
Report by NGO 7amleh, Utrecht University analyses 3,520 cases of digital rights violations against Palestinians.
‘Platformicide' of Palestine: Activists struggle to be heard on Meta
Report by NGO 7amleh, Utrecht University analyses 3,520 cases of digital rights violations against Palestinians.
www.aljazeera.com
August 12, 2026 at 9:00 PM
devincow.bsky.social
Science is fun www.sciencedirect.com/science/arti...
Sperm concentration remains stable among fertile American men: a systematic review and meta-analysis
Findings from several high profile meta-analyses have raised concerns about an ongoing global decline in sperm concentration and male fertility. Howev…
www.sciencedirect.com
May 11, 2026 at 8:21 PM
daniellebeckman.bsky.social
1 in every 4 kids will develop #LongCovid symptoms following Covid infection.
It is the result of an analysis of 8373 publications with a total of 80,071 children and adolescents.
Anyone denying this cannot be a Health Secretary anywhere.
www.nature.com/articles/s41...
Long-COVID in children and adolescents: a systematic review and meta-analyses Long-COVID in children and adolescents: a systematic review and meta-analyses
January 29, 2025 at 6:24 PM
boghuma.bsky.social
Tylenol is safe to treat pain and fever in pregnancy as well as in children. Talk to your health provider and follow evidence based practices.
onlinelibrary.wiley.com/doi/10.1111/...
Prenatal exposure to paracetamol and the risk of autism and attention‐deficit/hyperactivity disorder: An umbrella review and meta‐meta‐analysis
This meta-meta-analysis synthesizes evidence on prenatal paracetamol exposure and neurodevelopmental outcomes. Crude analyses suggest small associations with autism and ADHD, but these attenuate subs...
onlinelibrary.wiley.com
September 23, 2026 at 8:52 PM
numcog.bsky.social
New: "Effect of Artificial Intelligence on Learning: A Meta-Meta-Analysis" by Wagenmakers and colleagues revealing evidence for "severe publication bias and extreme between-study heterogeneity" in existing meta-analyses of the effects of AI on learning: osf.io/preprints/ps...
OSF
osf.io
February 10, 2026 at 2:52 PM
annadocherty.bsky.social
The PGC Suicide Working Group will provide a symposium at #WCPG2025 🇲🇽 covering our latest multi-ancestry GWAS and CNV meta-analyses, sex-specific meta-analyses, and GxEHR analyses. 🥳

@lcstoshio.bsky.social @andreyshabalin.bsky.social @sarahcolbert.bsky.social @caina89.bsky.social
October 19, 2025 at 6:18 PM
thelancet.com
What makes a meta-analysis believable?

In our latest issue, a new Viewpoint outlines how to identify meta-analyses that merit clinical confidence.

Explore the full issue: spkl.io/633277rxvt
Cover of The Lancet September 19, 2026 issue. Quote reads: Meta-analyses are not definitive truths, but rather structured efforts to interpret incomplete, evolving, and sometimes inconsistent evidence.
September 18, 2026 at 11:07 AM
profstevegriffin.bsky.social
7. Specifically, mask RCTs are inherently flawed, source control must be considered alongside protection.
8. RCTs can't account for complex behaviour.
8. Meta-analyses & systematic reviews are defined by their selection criteria, study weighting, and evidence hierarchy/idolatry.
December 12, 2025 at 11:07 AM
dsquintana.bsky.social
New preprint: Preregistration is supposed to make research more transparent. But if registry records aren't kept up to date, the transparency benefit erodes.

We checked 1,137 psych meta-analyses on PROSPERO and found the records are systematically out of sync with reality osf.io/preprints/ps...
Abstract Meta-analysis preregistration is intended to promote transparency and reduce research waste. However, it is largely unknown whether preregistration records accurately reflect the actual state of research, and how many preregistered meta-analyses are ultimately published in the field of psychology. We searched PROSPERO for preregistrations of psychology meta-analyses registered between 2011 and 2021 (n = 1137), verified publication status through systematic search, and contacted corresponding authors of unpublished registrations (n = 358) to obtain information on reasons for delays and discontinuations. We found that PROSPERO status labels were systematically inaccurate: 57% of records labelled "ongoing" were already published, and publication rates varied by registration status (Completed: 94%; Ongoing: 59%; Discontinued: 9%). Among 80 survey respondents, resource limitations were the primary reasons for project discontinuation (lack of time: 47%; lack of personnel: 11%; lack of funding: 7%) and preregistration quality showed no association with publication likelihood. Altogether, these findings suggest that PROSPERO registrations in psychology frequently fail to reflect the true status of a meta-analysis, undermining their value as a transparency tool, and that resource limitations frequently lead to meta-analysis abandonment. We recommend that journals and funders require registration updates at publication to reduce the accumulation of inaccurate and abandoned records. Figure 1. Overview of PROSPERO preregistrations of meta-analyses in psychology. (a) Number of psychology meta-analysis registrations per year (2011–2025); the dashed line marks the onset of the COVID-19 pandemic. (b) Publication status by year of registration (2011–2021). (c) Publication outcomes by PROSPERO registration status (Dark yellow = unpublished; Blue = published).
May 1, 2026 at 6:42 AM
neurozorro.bsky.social
Attention neuroscientsts!

We just launched Neurosynth Compose: A free and open platform for neuroimaging meta-analysis. NS-Compose makes it easy to perform custom neuroimaging meta-analyses without leaving the browser.

It's live, check it out! compose.neurosynth.org
neurosynth compose
Neurosynth-Compose App
compose.neurosynth.org
November 28, 2023 at 10:52 PM
drianweissman.bsky.social
COVID-19 vaccination during pregnancy conferred benefits for mother and baby without increased risk, according to an umbrella review of meta-analyses comprising more than 1.2 million women.
www.medpagetoday.com/meetingcover...
Mom's COVID Shot Aided Baby, Too, Large Review Confirmed
Vaccination during pregnancy was safe for both mom and baby
www.medpagetoday.com
October 1, 2025 at 2:32 AM
philosophie.gay
Meta-analyses & reviews are not better than randomized controlled studies. They are different levels of analysis. Plus, reviews rely on author bias & analyses can be skewed to show what you'd like. Yes you can do this with a trial, but no one else will be able to repeat it (because you cheated).
May 1, 2025 at 2:50 PM
georgiatomova.bsky.social
How many nutrition meta-analyses pool estimates for incomparable research questions, due to different energy adjustment strategies?

We looked at an illustrative sample. The answer was all of them!

Delighted to share our new meta-scientific review, led by @nataliaortega.bsky.social 👇
Meta-analyses of dietary exposures must consider energy adjustment: recommendations from a meta-scientific review
Abstract. In observational studies of dietary exposures, the energy adjustment strategy directly alters the effect being estimated. Adjusting for total ene
academic.oup.com
August 12, 2026 at 9:24 PM
matthewbjane.bsky.social
Most meta-analyses are bad, some are useful
April 29, 2025 at 5:30 PM
caulfieldtim.bsky.social
"Retracted studies can impact the results of meta-analyses."

Study: jamanetwork.com/journals/jam...

🚨 We MUST clean up academic literature! 🚨
Inclusion of Retracted Studies in Systematic Reviews and Meta-Analyses of Interventions
This systematic review and meta-analysis identifies reports of systematic reviews that included retracted studies in their meta-analyses, and assesses the impact of these retracted studies on the resu...
jamanetwork.com
April 1, 2025 at 4:32 PM
vickersbiostats.bsky.social
Too many meta-analyses have findings equivalent to: “If you average the cost of a loaf of bread, car insurance for a year and a movie ticket, you get $752.36”
January 26, 2026 at 11:41 AM
ericweinhandl.bsky.social
In general, meta-analyses of non-randomized studies give me the worst bellyaches.
November 19, 2024 at 5:00 AM