iiinova — where your digital self keeps evolving

Reposted by Heemin Kang

Dan Quintana @dsquintana.bsky.social · 28/05/2025

Papers are one-way conversations. Getting additional info from authors can be hard, so clear reporting from the outset is critical. In our new preprint, we (@annalschubert.bsky.social, Meike Steinhilber & @heeminkang.bsky.social) propose a set of psych reporting guidelines osf.io/preprints/ps...

Further resources on the interpretation of null results.

A dataset was generated showing simulated data points in two groups A and B. Group A follows a normal
distribution with a mean of 10 and a standard deviation of 1, while Group B exhibits a bimodal distribution, characterized by
peaks at 9 and 11 with a standard deviation of 0.5. As shown in the figure (A), barplots often fail to capture the true distribution
of the data. Although boxplots in (B) provide more insights into the data distribution compared to barplots, violin plots in (C)
and raincloud plots in (D) provide a more accurate representation of the actual data distribution. Reproducible code to generate
this figure is available at https://osf.io/mk5qa/.

Table 4. Overview of effect sizes for popular statistical models, with descriptions and software tools for estimation

16818