iiinova — where your digital self keeps evolving

Reposted by Suryadyuti Baral

Jonathan J. Park @jonathanpark.bsky.social · 29/08/2026

The GIMME framework is a method for analyzing heterogeneous time-series while identifying common dynamic patterns within samples. Happy to announce that we’ve extended it to the continuous-time framework in our new R-package, ctgimme! cran.r-project.org/web/packages...

cran.r-project.org

ctgimme: Continuous-Time Subgrouping with GIMME

Estimates group-, subgroup-, and individual-level dynamic structures from multivariate intensive longitudinal data using continuous-time state-space models. The subgrouping procedure combines iterativ...

1166

Reposted by Suryadyuti Baral

Marwin Carmo @marwincarmo.bsky.social · 07/01/2026

One of my New Year's resolutions was to be more active on social media again. Why not begin telling my tiny audience about my R package that was recently accepted to CRAN? The goal of `ivd` is to facilitate random effects selection with a spike-and-slab prior on the scale part of MELSMs.

111

Suryadyuti Baral @suryadyutibaral.bsky.social · 23/12/2025

Researchers study long developmental spans using accelerated longitudinal designs (ALDs). Fitting parametric growth or change score models imposes strong assumptions. We use functional data analysis to nonparametrically model ALDs in continuous time. Check out the preprint: osf.io/preprints/ps...

141

Reposted by Suryadyuti Baral

Amanda Kay Montoya @akmontoya.bsky.social · 15/01/2025

I've found myself more and more interested in, and teaching about collider bias. But I think for many it's pretty unintuitive and hard generate examples of. I'm trying out a new example in my course next week. We'll see how it goes. If you have tips or good examples, let me know!

A slide from powerpoint, where the title says "Visual Depiction of Collider Bias". The first paragraph says "Example: Assume Hardwork (Y) and Intelligence (X) are independent, but both impact college admissions (Z). If we control for college admissions in a model predicting Hardwork from Intelligence, this will bias the estimate of the X-Y causal effect (which should be zero)." On the left there is a scatterplot with Hardwork on the Y axis and IQ on the X axis. The datapoints on the graph are in an uncorrelated cloud. On the right, the points are colored by admission status, where the upper right of the cloud is mostly blue (admitted) and the lower left is mostly red (not admitted). The correlation for admitted is -.305 and the correlation for not admitted is -.294. In the bottom right of the slide it says "In a multiple regression, predicting HW from IQ and Admit…b = -0.03, p < .00001"

071

Reposted by Suryadyuti Baral

Mijke Rhemtulla @mijke.bsky.social · 06/12/2024

West-coast (ish) Quant-Psych(ometric) friends! Ben Domingue and I are organizing a small conference to be held in Davis in June. Please apply to attend, we're going to have so much fun. docs.google.com/document/d/1...

docs.google.com

2025 PQPC RFA

Request for Applications 2025 Pacific Quant Psych Conf (PQPC) June 26-27 2025 UC Davis Center for Mind and Brain in Davis, CA We would like to build a community of researchers on the west coast (and...

094

Suryadyuti Baral @suryadyutibaral.bsky.social · 20/11/2024

I worked on this project during my undergrad at UNC, and seeing it come to life as a preprint feels surreal. I feel incredibly proud to have contributed to such a remarkable project. Check it out and let us know your thoughts!

051

Reposted by Suryadyuti Baral

Wes Bonifay @wesbonifay.bsky.social · 11/11/2024

Looking forward to the @philsci.bsky.social conference this week where I will be standing next to this poster, in which my friend Hana and I ponder the concept of a "true parameter" in statistical modeling (zoom in here: shorturl.at/91gm5) #philsci

1413127