A modern introduction to statistical modeling, visualisation and mixed‑effects models for neuroscience research.
“Have you ever seen a hacker with a mouse?”
This button does not do anythingMost statistics courses present t‑tests, correlations, ANOVA, and regression as unrelated tools. This course reveals the deeper structure: they are all the same model. Understanding the linear model framework makes advanced neuroscience analysis efficient including mixed models.
Tour RStudio, install packages, and build a workflow that won't haunt you at 2 AM.
Import, clean, and summarize data with dplyr. What Excel takes hours to do, you'll do in seconds.
Build layered ggplot2 figures, embed stats, and combine plots. Make your data impossible to ignore.
Dissect Y=β₀+β₁X+ε term by term and mean-center X so your intercept finally makes sense.
Pearson vs. Spearman, z-scores, and the big reveal: scaling never changes the correlation.
Mix continuous and categorical predictors to isolate each variable's unique signal.
Formally test when the effect of A on Y changes with B. Spot moderation in the wild.
Add covariates to control confounds, or regress them out and work with clean residuals.
When trials nest inside subjects, classical regression lies. Meet fixed vs. random effects.
Write lmer syntax and watch "significant" effects vanish when random structure is correctly specified.
dplyr verbs, and generate publication-ready plots using ggplot2 instead
of relying on fragile spreadsheets.