Marieke A. Helmich

We built the openESM database:
▶️60 openly available experience sampling datasets (16K+ participants, 740K+ obs.) in one place
▶️Harmonized (meta-)data, fully open-source software
▶️Filter & search all data, simply download via R/Python

Find out more:
🌐 openesmdata.org
📝 doi.org/10.31234/osf...

Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities Abstract Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models).

Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve.

A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals). Illustrated are 1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals 2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and 3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.

Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...

🚨New paper (preprint, accepted at @psychscience.bsky.social journal AMPPS, with @herzog.bsky.social): a tutorial on conformal prediction, a distribution-free method for quantifying the uncertainty of predictions from statistical methods. Short 🧵 below!

osf.io/preprints/ps...

#PsychSciSky

How Accurate & Consistent are Self-Report responses via Visual Analogue Scales (VAS) in Ecological Momentary Assessment & Digital Studies?

Examined in a massive EMA study (N = 3,761), our new #OpenAccess piece on this is just out:

online.ucpress.edu/collabra/art...

#PsychSciSky #AcademicSky

🧵:

Cool perspective on depression recurrence

>19,000 observations, n=37 discontinuing anti-depressants

Recurrence in ~1/3rd preceded by early warning signals in affect

journals.sagepub.com/doi/epub/10....

Smit et al. @mahelmich.bsky.social @bringmannlaura.bsky.social @eveliensnippe.bsky.social

📣New preprint 📣

@leonieschorrlepp.bsky.social, @domimaciejewski.bsky.social, @bringmannlaura.bsky.social, Mithra Hesselink and I wrote a paper illustrating the value of qualitative methods for checking the validity of your ESM data.

doi.org/10.31219/osf...

Our new paper on self-reports vs clinician ratings of efficacies of psychotherapies for depression can be read open-access in Epidemiology and Psychiatric Sciences!

Here is a short summary of our findings🧵
www.cambridge.org/core/journal...

New work in @clinpsychrev: "EMA in psychotherapy research"

EMA:
✅ most used in clin *research*
✅ often to predict symptom changes
✅ rarely implemented to impact therapeutic processes
✅ research needed on actual EMA benefits in *practice*

www.sciencedirect.com/science/arti...

If you do ESM research, please fill out this Short ESM Survey on open-ended items. 🤓
You can fill it out even if you do not use open-ended items in your own ESM research (will be even shorter 😊) rug.eu.qualtrics.com/jfe/form/SV_...
.

Thanks for sharing, Daniel! 🙏 glad you enjoyed the paper

Fascinating study showing affective dynamics as predictors of depression relapse in those discontinuing anti-depressants

@ CPS by Smit, @mahelmich.bsky.social @bringmannlaura.bsky.social Oldehinkel Wichers @eveliensnippe.bsky.social

@psychscience.bsky.social

journals.sagepub.com/doi/epub/10....

How Accurate & Consistent are Self-Report responses via Visual Analogue Scales (VAS) in Ecological Momentary Assessment & Digital Studies?

Examined in a large EMA study (N = 3,761) w/L. Cloos @bsiepe.bsky.social @marilynpicciri1.bsky.social @eikofried.bsky.social @shirleybwang.bsky.social ... 🧵:

King's launches the Atlas of Longitudinal Datasets to support mental health research Researchers at the Institute of Psychiatry, Psychology & Neuroscience (IoPPN) at King’s College London have launched a new free platform to allow people to discover hundreds of longitudinal mental hea...

King's College London launches the Atlas of Longitudinal Datasets, in partnership with @wellcometrust.bsky.social / @mqmentalhealth.bsky.social, a free platform with over 1,600 datasets, to support mental health research worldwide. 🌍

Read more and learn how to access: www.kcl.ac.uk/news/kings-l...

Exciting news! 🎉 Registration for the 2025 SAA Conference is now OPENED!✨ Join us in the historic city of Leuven from May 26–28 for inspiring symposia, talks, workshops and networking! Don’t miss out—secure your Early Bird spot now! www.saa2025.com #SAA2025 #KULeuven @saa2025leuven.bsky.social

Our global study on the state of trust in scientists is now out in Nature Human Behaviour! 🥳

With a team of 241 researchers, we surveyed 71,922 people in 68 countries, providing the largest dataset on trust in scientists post-pandemic 👇🧵https://www.nature.com/articles/s41562-024-02090-5

Emotions are reactions to situations we encounter in daily life. In our new paper in Psych Review (psycnet.apa.org/fulltext/202...; with @oisinryan.bsky.social and @fdabl.bsky.social), we take a first step towards building a generative model for emotion dynamics based on this simple principle 1/4

Bookmark for all future grants: Use of Promotional Language in Grant Applications and Grant Success: "the percentage of promotional words was positively associated with the probability of receiving funding (NIH grants: odds ratio, 1.51 [95% CI, 1.10-2.11])." jamanetwork.com/journals/jam...

Social expectations in depression - Nature Reviews Psychology Expectations of negative social interactions or low interpersonal self-efficacy are common among people with depression. In this Review, Kirchner et al. integrate the cognitive, social and clinical as...

🍾New article out in @natrevpsych.bsky.social🍾:
We review how social expectations form and change in individuals with depression and how they shape the onset, course, and severity of depression. Particular emphasis is on why social expectations persist despite pos info.
www.nature.com/articles/s44...

📊 Key finding: Emotional improvements often precede behavioral changes, which may partly be due to smaller and less frequent behavioral changes. Cognitive shifts tend to align closely with mood changes. 📄 Link to the full paper: psycnet.apa.org/doiLanding?d...

I’m excited to share that @psypost.bsky.social featured our recent study on the timing of emotional, cognitive, and behavioral improvements during treatment for depression.
Co-authored with:
@mahelmich.bsky.social
@timonelmer.bsky.social
@arnoutcsmit.bsky.social
Wolfgang Lutz & Eva Ceulemans

🚨New Preprint on Affective Stress Responses in Daily life (N=248) - w/ @vizecolin.bsky.social and @aidangcw.bsky.social! We used high-density sampling after stressful events to closely examine the dynamic affective response following daily hassles by estimating latent microtrajectories. 1/3

Now that I understand starter packs, I've (re)started one for people interested in all things psychotherapy personalization and optimizing treatments to the individual 😊

Anyone welcome! And consider joining our Person-Centered Treatment and Prevention Collaborative group!

go.bsky.app/FXmURQf

I’d love to be added! Thanks for putting this together :)

Oh, I didn't realise it worked like that! Would be happy to share the PDF of course :) can you send me a DM or an email? marhelm @ uio.no

Thank you! 🙌

Wowed by the fact that the cover of the new @natrevpsych.bsky.social issue was inspired by our Perspective paper 🤩 read it here: rdcu.be/dWyLO

co-1st @schreudermj.bsky.social @bringmannlaura.bsky.social @harrietteriese.bsky.social @eveliensnippe.bsky.social @arnoutcsmit.bsky.social

I had a blast spending a whole week working on improving the measurement of intensive longitudinal data with so many smart and kind people. Like a nerdy school trip with friends. Thank you 🙏

@eikofried.bsky.social @bringmannlaura.bsky.social @miguelsilan.bsky.social Josip razum

#LorMITNB

Hi #LorMITNB forks, this may be useful of you want to follow other participants ; ) go.bsky.app/42Nh8oA

Amazing to see so many early career folks who care deeply about improving measurement of intensive longitudinal data
#LorMITNB