Dirk Pelt

The New Eugenics Companies Oops, I meant to say generational health and embryo selection

New blog post: The New Eugenics Companies
(Oops, I meant to say generational health and embryo selection)

Gefeliciteerd! En welcome back :)

How did I not know this banger?

For the love of god put the sample size in the abstract

We have a new preprint: this work is especially dear to my heart, as it results from the data collection pipeline we established at the Netherlands Twin Register, which enabled us to collect Facebook posts and likes (paid for with plenty of blood, sweat, and tears...)
osf.io/preprints/ps...

So cool! Congrats to the whole team!

Statistically Controlling for Confounding Constructs Is Harder than You Think Social scientists often seek to demonstrate that a construct has incremental validity over and above other related constructs. However, these claims are typically supported by measurement-level models...

Got it: journals.plos.org/plosone/arti...

Statistically Controlling for Confounding Constructs Is Harder than You Think Social scientists often seek to demonstrate that a construct has incremental validity over and above other related constructs. However, these claims are typically supported by measurement-level models...

Nevermind, got it! :)

journals.plos.org/plosone/arti...

Also tagging @dmcneish.bsky.social (it's driving me nuts that I can't find it..)

Kind of like when you have create a single indicator factor in a SEM model and fixing the residual variance of the indicator according to the (un)reliability. @michelnivard.bsky.social @dingdingpeng.the100.ci

Help! I recently came across a paper on regression in a structural equation modeling framework where the authors argued that results should be contextualized by assuming different levels of (un)reliability of the variables (or something along those lines). Now I can't find it anymore! Anyone?

Nederlands Tweelingen Register/BioPsy | LinkedIn Nederlands Tweelingen Register/BioPsy | 125 followers on LinkedIn. The Netherlands Twin Register is part of the Biological Psychology of the Vrije Universiteit Amsterdam (VU). Our research aims to exa...

NTR BioPsy is now active on BlueSky! Follow us for updates on scientific output from the Netherlands Twin Register and VU Biological Psychology department.

Also follow us on LinkedIn: www.linkedin.com/company/nede...

Broei!

Yes, something along those lines! Plus, what about scaling issues: those with very low baseline (between person) values simply have less wiggle room to vary downwardly. For traits that are correlated at the between person level, this induces correlations between within-person fluctuations then, no?

Very interesting! After reading this and your life satisfaction paper, I've been wondering how much of the variation we find is simply regression to the mean at the person level. Do you know any papers that systematically investigate/simulate this?

Thanks for the honor @behaviorgenetic.bsky.social !

This is neat! I am curious how much this approach differs from the work by Rosseel et al on factor score regression eg.

psycnet.apa.org/record/2023-...

journals.sagepub.com/doi/full/10....

Ai, goeie timing idd

Heb hetzelfde, ik moet naar de IT desk maandag..

Neat study! I have seen the same in our work, these individual slopes correlate with very little. I am wondering the extent to which these slopes simply indicate regression to the mean...