So excited to put this paper out into the world! Could not have done it without the help of such fabulous co-authors 😊😊

🚨PLEASE SHARE🚨 Do you live in a state that bans abortions? With the help of mail-forwarding, you can still get safe, effective abortion pills from a doctor in days. RT this thread to spread the word—so the people who need help learn how they can get it:

Bring a bill to a vote in the House and the Senate that legalizes abortion to save a woman’s life in all 50 states and force the Rs to vote it up or down. Then rape. Then incest. Make them vote.

Attending #IMPS2022? Come check out these talks by our lab, spanning topics such as validity, how we can leverage cross-sectional information, and intensive longitudinal data!

🚨 UC Davis Psychology (UC Davis UC Davis Psychology) is hiring for *THREE* tenure track positions this year in: (1) Personality: recruit.ucdavis.edu/JPF05140 (2) Anti-Racist Methods: recruit.ucdavis.edu/JPF05223 (3) Quant Methods: recruit.ucdavis.edu/JPF05224 #AcademicTwitter #AcademicChatter

Is there anyone who got the University of California President's Postdoctoral Fellowship and would be open to chatting/sharing application materials? #help #phdchat

How can we more appropriately choose control variables in our statistical models? If you're interested in hearing more about related challenges and potential solutions, join #ReproT with Anna Wysocki 👇 30 Nov! Sign up: shorturl.at/cxMR9 UK Reproducibility Network @ukrepro.bsky.social Swiss Reproducibility Network @swissrn.bsky.social Dr Jessie Baldwin

One of my favorite papers in recent years included this diagram. It shows the impact of controlling for three different types of variables: confounders, colliders, and mediators. With confounders, control is good. With the others, you ruin your result by controlling.

Thanks for pointing out Anna Wysocki's paper Statistical Control Requires Causal Justification. journals.sagepub.com/doi/full/10.11… I've almost given up on the psychology literature ever catching up to modernity. This paper promises to do it. Recommended.