GLM and Statistical Testing Illustrated

This lecture covers the General Linear Model (GLM) and statistical testing in the context of neural signals and signal processing. It explains the theoretical model, contrasts, Gauss-Markov assumptions, fitted models, multiple comparisons using Bonferroni, Gaussian random field, False Discovery Rate (FDR), and cluster size analysis. The instructor also discusses the importance of F-tests, region-of-interest analysis, statistical inference, and group-level analysis. Additionally, it delves into functional connectivity, resting-state fMRI, multivariate methods like Principal Component Analysis (PCA) and Partial Least Squares Correlation, and the analysis of variance (ANOVA) models.