Fun fact about LMMs: when you have missing data, power also depends on the correlation between intercepts and slopes. In the clip, I’m varying the amount of random slope variance.

Just added to PowerLMM.js v0.3: Interactive power contour plots!

Visualize how statistical power changes across parameter combinations.

powerlmmjs.rpsychologist.com?view=contour

Power analysis summary report, that can be printed or saved as a PDF

Hypothesis region visualization. Interactive display of the chosen null and alternative hypothesis.

Added a variogram to the app!

I'm experimenting with showing the non-stationarity of correlations in a random slopes model.

Added a simple illustration of group trends to demonstrate what the effect size represents

Just deployed some small updates:

More tooltips!

Offloaded the most expensive computations to background threads, and added a cheeky loader for the inevitable scenario where someone tries to inverse huge matrices at 60fps+.

To better understand the random effect parameters, you can view a sample of 20 random slopes adjusted to match the exact variance and correlations specified

Dropout can be specified using either a Weibull distribution or manually

Introducing PowerLMM.js!

A new tool for power analysis of longitudinal linear mixed-effects models (LMMs) – with support for missing data, plus non-inferiority and equivalence tests.

powerlmmjs.rpsychologist.com

Would really appreciate your feedback as I refine this app! Details below 🧵👇