Lightnews — Scholar-powered news

Jonas Haslbeck @jmbh.bsky.social · 16d

We found that model selection was successful for state separations similar to the ones we found in empirical data and estimation error was satisfactory for realistic numbers of observations and subjects.

1

Jonas Haslbeck @jmbh.bsky.social · 16d

Going beyond existing simulations, we independently varied the number of true states, the state separation, the number of variables, the number of time points, and the number of subjects.

1

Jonas Haslbeck @jmbh.bsky.social · 16d

In the second paper (osf.io/preprints/ps...) we conduct an extensive simulation study to evaluate whether existing software works as intended and how well multilevel HMMs can be estimated in typical time series designs in psychology.

OSF

osf.io

1 1 2

Jonas Haslbeck @jmbh.bsky.social · 16d

In the first paper with Emmeke Aarts (osf.io/preprints/ps...) we provide a gentle introduction to (multilevel) HMMs and walk the reader through a fully reproducible tutorial on model specification, estimation, selection, and interpretation by analyzing a typical EMA emotion time series dataset.

1 1 2

Jonas Haslbeck @jmbh.bsky.social · 16d

While Emmeke Aart's R-package mHMMbayes already allows estimating multilevel HMMs, there has been no easily accessible tutorial on how to use these models and no evaluation of how well these models can be estimated in situations typical for psychology research.

1

Jonas Haslbeck @jmbh.bsky.social · 16d

Two new preprints on multilevel HMMs! Time series data is now pervasive in psychology and new methods are needed to model the dynamics in such data. Hidden Markov Models (HHMs) are powerful models for dynamics in which a system is switching between a number of discrete states.

2 21 66

Reposted by Jonas Haslbeck

Lorentz Center @lorentzcenter.bsky.social · 16d

Experts with theoretical traditions, researchers experienced in approaches to theory construction, educators and policymakers work on the first steps toward creating a mature subfield of theoretical psychology. bit.ly/4nLOWoE @annemscheel.bsky.social @bringmannlaura.bsky.social @jmbh.bsky.social

2 7

Reposted by Jonas Haslbeck

Fabian Dablander @fdabl.bsky.social · Jul 23

Are climate activists portrayed as polarising & violent in the news media? Are risks & solutions to climate change mentioned?

We used ChatGPT to answer these questions based on > 4,200 articles from seven major German newspapers: link.springer.com/article/10.1... w @jmbh.bsky.social & Simon Wimmer

1 7 12

Jonas Haslbeck @jmbh.bsky.social · Jun 10

Thanks, but I'm afraid also this link doesn't work for me (requires a KU Leuven login)

1

Reposted by Jonas Haslbeck

Julia Carrie Wong @joolia.bsky.social · May 8

“States must act now to end the violence or bear witness to the annihilation of the Palestinian population in Gaza – an outcome with irreversible consequences for our shared humanity”

End unfolding genocide or watch it end life in Gaza: UN experts say States face defining choice

GENEVA – Escalating atrocities in Gaza present an urgent moral crossroads and States must act now to end the violence or bear witness to the annihilation of the Palestinian population in Gaza – an out...

www.ohchr.org

3 150 230

Reposted by Jonas Haslbeck

Amsterdam Complexity School on Climate Change @acscc.bsky.social · May 2

What a show on the last day of ACSCC 2025 where our brilliant participants presented the culmination of their week-long collaborations. Buckle up for today’s highlights👇

1 2 4

Reposted by Jonas Haslbeck

Amsterdam Complexity School on Climate Change @acscc.bsky.social · Apr 30

Time flies and we are already halfway through ACSCC!

Today was kicked-off by @doynefarmer.bsky.social, who gave us a deep dive into forecasting technological progress. Doyne also shared his vision of complexity economics for a better world, and showcased his impressive modelling work at Macrocosm.

1 3 6

Reposted by Jonas Haslbeck

Amsterdam Complexity School on Climate Change @acscc.bsky.social · Apr 29

The second day of ACSCC was again full of inspiring lectures and discussions!

Day two was kicked-off by the keynote of Tim Lenton, who gave an introduction to tipping points and an update on the latest research, followed by a discussion about effective leverage points using positive tipping points.

1 4 8

Reposted by Jonas Haslbeck

Amsterdam Complexity School on Climate Change @acscc.bsky.social · Apr 28

The second edition of ACSCC is officially underway!
We had a fantastic first day, welcoming over 40 participants from a wide range of disciplines — including economists, lawyers, social scientists, metallurgists, and more. Once again, we are blessed with wonderful sunny weather here in Amsterdam! ☀️

1 4 7

Reposted by Jonas Haslbeck

Amsterdam Complexity School on Climate Change @acscc.bsky.social · Apr 24

We are very excited about the line-up of speakers for ACSCC, which kicks off next week!

The following talks can also be followed online:

Tim Lenton: tinyurl.com/5d9ubts9
Joyeeta Gupta: tinyurl.com/kbk92rap
Doyne Farmer: tinyurl.com/vdrhjvwe
Vítor Vasconcelos: uva-live.zoom.us/j/89976716302

Line-up of our speakers: Tim Lenton, Doyne Farmer, Joyeeta Gupta, Liesbeth van Tongeren, Vitor Vasconcelos, Ben Franta, Heleen Ekker, Lydia Baan Hofman, Erika van der Linden, Pippi van Ommen, Agat Sharma, Laura Cull O Maoilearca

1 2

Reposted by Jonas Haslbeck

SAA 2025 Leuven @saa2025leuven.bsky.social · Apr 2

How can Multilevel Hidden Markov Models help uncover personalized dynamics? Find out in the post-conference session on May 29 with Emmeke Aarts (Utrecht University), Jonas Haslbeck (University of Amsterdam), and Pepijn Vink (Utrecht University)! @jmbh.bsky.social

SAA 2025

Society for Ambulatory Assessment Conference 2025

www.saa2025.com

1 8

Reposted by Jonas Haslbeck

Eiko Fried @eikofried.bsky.social · Feb 13

1/3

Tutorial on exploring ecological momentary assessment data is online at AMPPS, with:
- Accessible ways to visualize data for better understanding
- Models to get some first insights
- Further reading boxes for more advanced topics
- Reproducible pipeline you can run over your own data

6 78 150

Jonas Haslbeck @jmbh.bsky.social · Feb 13

... and provide a fully reproducible step-by-step tutorial on model estimation, selection, diagnostics and interpretation.

1

Jonas Haslbeck @jmbh.bsky.social · Feb 13

... we valuate how well these models can be estimated in typical empirical settings using a simulation study ...

1

Jonas Haslbeck @jmbh.bsky.social · Feb 13

...we provide an introduction to LCVAR models, introduce the new R package ClusterVAR (cran.r-project.org/.../pack.../...)

cran.r-project.org

2 1 1

Jonas Haslbeck @jmbh.bsky.social · Feb 13

New preprint by Anja Ernst and me on Modeling Qualitative Between-Person Heterogeneity in Time-Series using Latent Class Vector Autoregressive Models (osf.io/preprints/ps...)

1 1 5

Jonas Haslbeck @jmbh.bsky.social · Feb 1

Was also confused and just uploaded everything as a PDF again (:

Reposted by Jonas Haslbeck

Fabian Dablander @fdabl.bsky.social · Jan 24

🚨 New preprint! 🚨

We analysed over one million actions reported in the AWorld app, the UN's official platform for individual action on climate change: osf.io/preprints/ps...

This was an exciting collaboration with @kristiansn89.bsky.social, Jan Bauer, Laura Basconi, & @cameronbrick.bsky.social 🧵👇

4 13 28

Reposted by Jonas Haslbeck

Karoline Huth @karolinehuth.bsky.social · Jan 24

Are psychometric networks sufficiently supported by data such that one can be confident when interpreting its results? We analysed 294 psychometric networks from 126 papers with the Bayesian approach to address this question @jmbh.bsky.social Sara Ruth van Holst @maartenmarsman.bsky.social 🧵

PsyArXivBot @psyarxivbot.bsky.social · Jan 16

Statistical Evidence in Psychological Networks: A Bayesian Analysis of 294 Networks from 126 Studies: http://osf.io/62ydg/

1 16 51