Kristoffer Magnusson @rpsychologist.com · Jun 25 New interactive blog! "Why Adjusted Regression Coefficients Are Less Descriptive Than They Look" rpsychologist.com/descriptive-...
185 likes 13 replies
Replies
Useful interactive! But I'd say it's not clear you'd want to adjust for these if looking at the causal effect of income... presumably they are at least partially affected by income.
This is incredible! Thank you so much, I'll use it in my classes!
This is fantastic!! The message is communicated so clearly, both via words and visuals. After reading this, I immediately added it to my grad stats syllabus. Thank you!!
@danlewer.bsky.social 👀☝️ (Lewer et al., 2025)
This is excellent! I wish all teaching materials were like this. 👍
This is great! Will bookmark for teaching
“There is no such thing as the association.” @jeremylabrecque.bsky.social your kind of energy!
Trying out Svelte for the first time here btw, really like it so far. Not sure why I didn't switch years ago.
1/2 Good job spreading the word. I find it really difficult, almost impossible, to justify using conditional estimates for purely descriptive goals without using the notion of counterfactual dependence, which arguably changes the goal from description to CI.
Excellent post and nice summary at the end! The plot in the GIF is particularly nice.
I wish I'd had access to this blog post the last time I wrote a review! Would have definitely linked it to the authors who wanted to test associational hypotheses using heavily adjusted regressions.
This is brilliantly clear and beautifully illustrated.
How do you keep coming up with these? 👏 Excellent both in content and in visual display. Thank you for these, I always use your site in teaching.