Penn State faculty are forming a union. It's long overdue. Please share widely, friends. www.pennstatefacultyalliance.org

Jorgensen & Garnier-Villarreal have a helpful paper showing several failures with "small-variance priors" in Bayesian SEM doi.org/10.1007/978-... These priors will fail for the types of misspecification we create in simulation studies, wrote a blogpost: www.jamesuanhoro.com/post/2024/11...

I open this website from time to time, and usually expect to have no notifications. So why did I come on here this morning to 30+ notifications? @stephenjwild.bsky.social, did you do something?

Started work on a Bayesian SEM package in February. I use it in my work and I think it's now a reasonably useful package. minorbsem: jamesuanhoro.github.io/minorbsem/ Unique(?) features: 1. models assume random error is a given in applied SEM, including Wu & Browne RMSEA model ...

This is a very specific type of problem. I show how I might set up an informative (left-skewed) prior for a regression coefficient based on a single published result. The gist contains a brief narrative and R code for finding the distribution parameters. gist.github.com/jamesuanhoro...