Dr. Michèle Nuijten

@MicheleNuijten@sciences.social
679 Followers
354 Following
21 Posts
Assistant Professor at Tilburg University. Research on meta-science, incl. topics such as replication, publication bias, statistical errors, and QRPs. Developer of #statcheck
Websitehttps://mbnuijten.com
Statcheckhttp://statcheck.io
PronounsShe/her

Very excited to announce a second PhD position!

In this project, you will look at the statistical validity of psychological intervention studies.

Perfect for students interested in clinical psychology, statistics, methodology, and meta-research.

The {statcheck} #rstats 📦 is “a ‘spellchecker’ for statistics. It checks whether your p-values match their accompanying test statistic and degrees of freedom.”

statcheck searches text for null-hypothesis significance tests in APA style (e.g., t(28) = 2.2, p < .05), recalculates each p-value, and flags errors if reported and computed values don’t match.
By @MicheleNuijten
Repo: https://github.com/MicheleNuijten/statcheck
#ESMARConf2023 Video: https://youtu.be/XuFyqXw5ho0
@rstats #stats

GitHub - MicheleNuijten/statcheck: A spellchecker for statistics

A spellchecker for statistics. Contribute to MicheleNuijten/statcheck development by creating an account on GitHub.

GitHub

REMINDER!! You have until the 7th of April to apply! >>>

🚨 PhD position in meta-research 🚨

What? Assess the effectiveness of interventions to improve psychological science

With whom? Me & @JelteWicherts

Where? Meta-Research Center,
Tilburg University

Why? Creative research w impact & great colleagues!

Details: https://tiu.nu/21373

Job opening: PhD position in meta-research: The effectiveness of interventions to improve psychological science (21373)

🚨 PhD position in meta-research 🚨

What? Assess the effectiveness of interventions to improve psychological science

With whom? Me & @JelteWicherts

Where? Meta-Research Center,
Tilburg University

Why? Creative research w impact & great colleagues!

Details: https://tiu.nu/21373

Job opening: PhD position in meta-research: The effectiveness of interventions to improve psychological science (21373)

Linking Jelte: @JelteWicherts

🔢 You can find the preregistration, data, and R code here: https://osf.io/q84jn/

🤖 Interested in #statcheck? Check out the latest version on http://statcheck.io.

Estimating the effectivity of statcheck in peer review to reduce statistical reporting inconsistencies

We compare the prevalence of statistical reporting inconsistencies between journals that implemented statcheck in their peer review process and matched control journals, before and after statcheck implementation. Hosted on the Open Science Framework

OSF
Plans for exploratory analyses: we noted that even after statcheck implementation, some articles still contained statistical inconsistencies 🤔. We will dive deeper in full text of a subsample of these cases to see what is going on here. Suggestions for additional analyses are welcome! 🧮
An important limitation of our study is that it is observational: by including matched control journals we aimed to reduce confounding factors, but we can’t fully rule out alternative explanations (e.g., maybe authors who are more careful in stat reporting prefer a “statcheck” journal).

These results provide initial evidence that using #statcheck in peer review may be a successful intervention to decrease statistical reporting inconsistencies. 🤖✅

but... >>

We used preregistered multilevel logistic regression analyses to predict (decision) inconsistencies and found a significant interaction effect of journal_type*time in the expected direction: a steeper decline in (decision) inconsistencies in statcheck journals than matched controls.