I told a story at my lab meeting today about the time I met John Cougar Mellencamp…and none of my grad students had heard of him. I must be nearing the end of my days…

It feels like all of our graduate students are defending their dissertations this spring...and I am on all of their committees.

In IRT modeling, shouldn't the 1PL model have one more degree of freedom than the Rasch model? In the 1PL I am estimating a common discrimination parameter where the Rasch model sets it to 1. But the mirt package in R is saying they have the same number of parameters.

Ok. I've convinced myself that the RI-CLPM model is not appropriate for modeling constructs that are systematically growing/changing over time. These data don't meet the assumptions of the model. But I keep seeing it getting recommended for developmental studies. Am I missing something?

I may not know much, but I know a model with -5 degrees of freedom is not going to fly.

I was teaching when the active shooter warning came. I can tell you the one thing I was not prepared for. Trying to determine if we should stay in the classroom and start building barricades vs. evacuating the classroom for a more defensible position. Was it safe to let my students in the hallway??

Next week, I'm teaching a 3-day workshop on DSEM for intensive longitudinal data using Mplus and registration is still open -- more information about the topics and registration can be found here! statisticalhorizons.com/seminars/dyn...

Loving this paper, Getting Started with Data Sharing: Advice for Researchers in Education! #datamgmt #edresearch #datasharing @cmwhite.bsky.social @sestrera.bsky.social @schotz.bsky.social and Sara Hart osf.io/preprints/ed...

The end of the semester is approaching! Teaching random factors in my ANOVA course today!

Has someone made a shit-poster starter pack? A list of accounts that post snarky comments, random puns, or lighthearted statistical modeling jokes?

I want to investigate reciprocal relations between two variables over time (let's say I have at least 4 points). These variables have not reached "equilibrium" - that is, the kids are still growing on both variables. What model would you choose? Dual Latent Change? RI-cross lagged? Something else?

I know it’s pronounced Blue Sky, but brain keeps pronouncing it Blueskee.

Roofing houses Interior/exterior painter Security guard Worked a press at a tool and die Towel cage at a gym Research assistant Post-doc Professor

New double special issue on "Open Science and Data Protection" in JOAL, and it really has everything: - philosophy of openness - technological sovereignty - sharing of health data - informed consent - AI and open science 1: ojs.law.cornell.edu/index.php/jo... 2: ojs.law.cornell.edu/index.php/jo...

I am looking for institutional statements supporting open science practices and scholarship. If you are part of an institution or organization that has made a policy statement about how open science will be encouraged and supported-can you drop a link to that statement in reply? Thanks! #openscience

Do you do Structural Equation Modeling in #rstats? The main developer of one of the primary packages, #lavaan, is running into trouble securing funding to keep the package going, and has reached out to the community to help support. Donate here: lavaan.ugent.be/about/donate...