Ruben Arslan @rubenarslan@schelling.pt

I would be interested to hear what someone who knows more about quantile regression thinks about this @alexpghayes @PHuenermund

thanks to @smartin2018, whose LMMSELM package gets an honorary mention, for comments
https://github.com/stephenSRMMartin/LMMELSM

New blog post on the Killingsworth, Kahneman, Mellers paper and censored mixed effects location-scale models.
TLDR: sampling error, censoring, and heterogeneous within-subject variance could all bias the KKM estimates. Better models exist (with brms)

https://rubenarslan.github.io/posts/2023-03-05-multilevel-censored-location-scale-models

I don't think there's nothing substantive to these trends, but, man, I don't trust that gang with their thirst for monocausal explanations to get to the bottom of this or anything else really.

Ah yes, the good old "we tried chopping up the data many ways to find a specific three-way-interaction we had in mind". You love to see it in 2023.

Working with Malte is wonderful! If this project interests you, apply, if it doesn't consider developing an interest so you can apply.
---
RT @maltoesermalte
Job opportunity at my lab in a project on privacy in mental health apps, done in collaboration with the Clinical Psych and Psychotherapy division (Thomas Berger). Starts in July, funding for 4 years. If you like open science and research methods, please apply until March 31. ht…
https://twitter.com/maltoesermalte/status/1633425351903772672

in which @Aella_Girl is an exemplary collider, which, all things considered, probably is something she aspires to
---
RT @the100ci
New post! Are representative samples redundant at best? @dingding_peng investigates 3 scenarios: estimating a prevalence, estimating a causal effect in an experiment, and estimating a causal effect (or a correlation!) in an observational study. https://www.the100.ci/2023/03/07/non-representative-samples-what-c…
https://twitter.com/the100ci/status/1633114722680569857

OK, time to spill it: When you prompt ChatGPT with a Stackoverflow question template to get help with R programming, whose name do you put in as the person answering?

If anything, I see this episode as evidence that adversarial collaborations with a massive power differential don't work.
Like, income explains <1% in well-being. It's loglinear, i.e. diminishing returns. But there has to be a threshold too? How much cope do you need?
---
RT @rubenarslan
@AaronCharlton If I fit a spline on the 15% quantile, it doesn't seem like the threshold is 100k either, more like 200k. Not that this nonlinear fit i…
https://twitter.com/rubenarslan/status/1631661372126687232