Michel Nivard

@michelnivard.bsky.social

571

Followers

609

Following

1369

Posts

Professor of Genetic Epidemiology, University of Bristol.

Posts Replies Media Feeds

Reposted by

Michel Nivard

We're working on complexity approaches to atypical development, and are looking for a unicorn of a dataset: N>200, ADHD or ASD (either continuous symptoms or diagnosis yes/no), but above all, Trials>500 on a cognitive task (ideally with a continuous outcome measure, e.g. RT). #PsychSciSky #ESM

Hey #sociology and #demography bluesky! What’s the definitive source on uk/english cultural geography? Looking for MSOA or Local authority level, possibly catagorical socio-cultural classifications.. not electoral, urbanicity, or density, but classifications of regions based in culture…

Scrolled a friends “following” (normy global culture/football/politics) his “for you” was was basically 70% horror show, though it was my friends algo, asked two more to let me take a peak totally same. Totally context collapsed ID(Freudian sense)/4-chan hamster wheel… 🧵1/2

Dipping back into Twitter to lurk on assassination stuff and truly, from the bottom of my heart, unless you have massively curated lists, no one in media or politics should be microwaving their neurons on there.

Never knew I would one day do the very clickbaity “omg my kids math homework!” But wtf is this…

Just found an R package that is an absolute work of art 10/10 no notes… It pains me to admit it’s very Bayesian 😂

Reposted by

Michel Nivard

Me after learning about collider bias

🇫🇷 phew.... nothing to be complacent about, but still...

The more things change…

I feel seen…

"would you give my paper a quick read, see if there’s anything more i could do?" the paper:

Then I learned that emeritus prof David Firth (of “firth regression” fame) also developed the UK exit poll!

What time will we know who won? Hour-by-hour guide to election nightwww.theguardian.com Want to catch a few results before bed, or see it through to the moment of reckoning? We’ve got you covered

This feel like the highest praise I ever got as a person who sometimes cosplays as an software developer... (the RMarkdown inventor mentioning me on github, but on a thing I never got to work eventually...)

Reposted by

Michel Nivard

good news, everyone

@eikofried.bsky.social I ran into your Eiko Bot alter ego!

Reposted by

Michel Nivard

I am so honored to have won the Dobzhansky Award at BGA in London. Puts me in mind of my mentors who won it before me: John Loehlin, Sandra Scarr and Irv Gottesman. Many others, of course. I don't belong in that company, but it was sure a beautiful setting.

Reposted by

Michel Nivard

Tip: We aren't comparing the effect of the treatment (tx) to the effect of placebo. We are *defining* the effect as the *difference* in outcome between those allocated to standard of care (SoC) + tx to those allocated to SoC + placebo, where placebo is used for blinding.

Reposted by

Michel Nivard

Sharing some updates on my positconf::2024 slides 🧵

I think the technical term for the current state of global politics is “fuckidyfuckfuck”…

JUST IN: Polls closed in first round of France elections. Two main French TV estimates (combines early results & exit poll) show strong far-right. Far-right bloc: ≈34% Left bloc: ≈28-29% Macron bloc: ≈20-22% What does this mean? What'll happen? Follow this thread ⬇️

#BGA2024 was a blast!! What’s venue, amazing science (best in years), ended on a high note with an amazing banquet & heartfelt words by @ent3c.bsky.social

I just payed all this, which is fine I have incredible opportunities and a well paying job. But it’s prohibitive for early career talents to pay ~10k up front and similar high sums for spouse and kids for a 5 year visum and healthcare (on top of regular NHS costs) www.theguardian.com/education/ar...

Top scientists turning down UK jobs over ‘tax on talent’, says Wellcome bosswww.theguardian.com Next government urged to lower upfront visa costs that are 17 times higher than international average

#stats #uk this desk is right behind passport control in Heathrow, never felt more welcome!

Reposted by

Michel Nivard

Reply to

Andrea Ganna

Second, we show that the variability in polygenic score performance is larger between biobanks than between the methods used to build the scores t.co/ESmOPB8vr9

Evaluation of polygenic scoring methods in five biobanks shows larger variation between biobanks than methods and finds benefits of ensemble learningt.co Methods of estimating polygenic scores (PGSs) from genome-wide association studies are increasingly utilized. However, independent method evaluation i…

Reposted by

Michel Nivard

Ehi Bsky community, I have been neglecting you! Just want to report some recent work from our team. Let's start with this paper on the causes for loss of chromosome X in women www.nature.com/articles/s41...

Genetic drivers and cellular selection of female mosaic X chromosome loss - Naturewww.nature.com A large-scale meta-analysis across eight biobank datasets identifies common genetic variants associated with mosaic loss of the X chromosome in female participants.

Reposted by

Michel Nivard

If an effect falls in a forest and no one is there to determine the mechanism, is it even causal? New post in which I try to clarify some things--claims about causal effects are indifferent to mechanisms; heterogeneity does not invalidate average estimates. www.the100.ci/2024/06/26/s...

Sometimes a causal effect is just a causal effect (regardless of how it’s mediated or moderated)www.the100.ci TL;DR: Tell your students about the potential outcomes framework. It will have (heterogeneous) causal effects on their understanding of causality (mediated through unknown pathways), I promise. It’...

I want to become latent myself, a methodologist who transcends… free of error… my physical self abstracted into an ill defined low dimensional Psy matrix that people then take way to seriously for a few decades. (Zen Sufism -> SEM Sufism…)

Dutch kids hustling… (is this because we have a lower youth minimum wage making them relatively cheaper labor, or is a age specific minimum wage a normal practice across Europe?)

There is something very exciting about flipping trough a conference program where you know (of) more than 80% of the speakers 💕

Reposted by

Michel Nivard

`tinyplot` is now available on CRAN. 🎉 tl;dr `tinyplot` is a super lightweight extension of the base #rstats graphics system that makes it easy to draw sophisticated plots with minimal overhead. See our website for more examples and a detailed intro tutorial. grantmcdermott.com/tinyplot/

New Dutch hard right wing government taking a hammer to higher ed… It looks like an up to 1 billion euro (8/10%?) budget cut across science and education side of the business. Most onerous is the direct reversal of a program that’s just put 1200 talented scientists in a permanent jobs.

Toponderzoekers zien in bezuinigingsplan van nieuw kabinet ‘vertrouwensbreuk met wetenschap’www.nrc.nl Open brief van laureaten: Geplande bezuinigingen van het komend kabinet bij universiteiten kosten vele honderden onderzoeksbanen en tasten innovatie en het…

R2 (and prediction) can be very strange!

This well-known paradox of R-squared is still buggin me. Can you help me out? statmodeling.stat.columbia.edu/2024/06/17/t...

This well-known paradox of R-squared is still buggin me. Can you help me out? | Statistical Modeling, Causal Inference, and Social Science statmodeling.stat.columbia.edu

We’re late, we’re behind, and there are plenty useful idiots that want to live with the fiction that climate change isn’t real. But we’re also on a steep trajectory to seriously reduce emissions (UK emissions per KWh, source: grid.iamkate.com )