PhD Student in Psychological Methods | Time series, networks, simulation studies & open science | @bsiepe.bsky.social
Marburg, Germany
Joined July 2020
- Tweets104
- Following265
- Followers328
- Likes804
Pinned Tweet
We reviewed 100 psych. simulation studies & find room for improvement in planning/reporting. As a remedy, we (@BartosFra, @tmorris_mrc, @BoulesteixLaure, @Daniel_W_Heck & Samuel Pawel) present ADEMP-PreReg, a sim study preregistration & reporting template
osf.io/ufgy6/
ALT summary of the ADEMP reporting structure
Björn Siepe retweeted
Have you run #simulation studies and encountered issues with missing results, failure, or non-convergence? In a new preprint by Samuel Pawel, @b_siepe & @annloh, we overview different approaches to address missingness and review current practices.
arxiv.org/abs/2409.18527 #Stats
Björn Siepe retweeted
New preprint by @b_siepe & WARN-D team.
We collected information on sleep, tiredness & stress with both EMA and sensor data, and try to find out to which degree these are associated contemporaneously in a large dataset (n~800) with many timepoints (t~360).
Brief 🧵
Just in time for conference season: Our paper on simulation studies in psychology was accepted at Psychological Methods! 🥳See the thread below for a summary, the updated preprint is available at doi.org/10.31234/osf.io/ufgy…
We reviewed 100 psych. simulation studies & find room for improvement in planning/reporting. As a remedy, we (@BartosFra, @tmorris_mrc, @BoulesteixLaure, @Daniel_W_Heck & Samuel Pawel) present ADEMP-PreReg, a sim study preregistration & reporting template
osf.io/ufgy6/
ALT summary of the ADEMP reporting structure
Björn Siepe retweeted
The 1st talk in Measurement & Reasoning is “Simulation Studies for Methodological Research in Psychology” by Björn Siepe @b_siepe
mathpsych.org/presentation/1…
#iccmpsyched
Björn Siepe retweeted
Should you use Likert or VAS for EMA research?
In a new paper led by @jonashaslbeck & @AlbertoJover (last author @EatingLab), we assigned n~160 in a 2 week study to either
📏1-7 Likert or
🎚️1-100 Visual Analogue Scale
and compared results using Bayesian multilevel models.
Brief thread with results.
Comparing Likert and Visual Analogue Scales in Ecological Momentary Assessment osf.io/yt8xw/
Björn Siepe retweeted
For those of you who are into prediction, considering joining this fascinating challenge run by my colleague @Gert_Stulp_or_G !
You will be asked to predict who will have a child in the next three years based on both panel survey data and administrative data.
Björn Siepe retweeted
1/8 New tutorial preprint led by @b_siepe in which we present different descriptive statistics & data visualization techniques with the goal to better understand EMA item functioning.
Preprint: osf.io/preprints/psyarxiv/dv…
Brief overview thread 🧵:
Björn Siepe retweeted
1/4 FRED is online, our free open source software to provide feedback to participants in EMA studies.
We (led by @AljoschaRimpler) programmed the software to provide feedback at scale to our ~2000 WARN-D participants. Hope it will be useful to researchers & clinicians alike!
Maybe someday I will have the courage to actually go for the pun in the title... Until then, check out our new preprint on multiverse for dynamic network/GIMME models, featuring ~750k individual networks and a shiny app to explore results
This Post is from an account that no longer exists. Learn more
Björn Siepe retweeted
Thanks to @b_siepe @BartosFra and S. Pawel for involving me in this exciting project together with @tmorris_mrc and @Daniel_W_Heck on planning and reporting of simulation studies (using ADEMP) in psychological methods research!
We reviewed 100 psych. simulation studies & find room for improvement in planning/reporting. As a remedy, we (@BartosFra, @tmorris_mrc, @BoulesteixLaure, @Daniel_W_Heck & Samuel Pawel) present ADEMP-PreReg, a sim study preregistration & reporting template
osf.io/ufgy6/
ALT summary of the ADEMP reporting structure
We provide Monte Carlo standard error calculations and sample size planning formulas for the most common performance measures and showcase the ADEMP methodology in an example simulation study.
ALT Large table with performance measures, their definition, their estimates, MCSE, and number of repetitions
Björn Siepe retweeted
👇 REGISTRATION OPEN! 👇
tinyurl.com/OpenScienceDays2…
📢 #OpenScience Days Marburg, part of #BrainhackGlobal 2023!
🗓️ Dec 4-5 in 🏰 Marburg, Schulstrasse 12
🏫 mornings: short intensive talks
💻 afternoons: hands-on sessions & project work
💬 tuesday 4pm: Open Science discussion
Preprint on Bayesian estimation and testing for idiographic networks (psyarxiv.com/uwfjc/)🎉
Networks on n=1 data are popular, but they often contain a lot of noise. How can we test if networks that look different reflect more than sampling variability?
🧵below
💻Test & additional plotting functions (see below for an example on posterior uncertainty coefficient matrix) implemented in the R package 'tsnet' on GitHub (github.com/bsiepe/tsnet); all code available on OSF. Joint work with @Daniel_W_Heck.
ALT A plot containing a matrix of posterior distributions, shaded based on the magnitude of an effect.
We 1) evaluate an existing Bayesian method to estimate idiographic networks & 2) propose a novel test that evaluates the evidence that differences in edges between two models are not just due to sampling variability. We then apply estimation & test methods to empirical data.