Abstract:
|
Neuroimaging studies routinely collect and analyze large samples of spatiotemporal data. For example, a typical fMRI study records data from thousands of voxels (3D volumes) over the course of an experiment, which could last several minutes or hours. In many neuroimaging studies, the goal is to understand how differences in brain activity relate to individual differences in psychological constructs, e.g., personality or intelligence. The statistical analysis of neuroimaging data often consists of two (or more) stages: (1) apply some dimension-reduction technique, and (2) fit a regression or classification model to the reduced data. In this talk, I will discuss how these two stages can be combined into a single statistical framework for relating brain activity to psychological outcomes.
|