Abstract: I will discuss the primary statistics-in-neuroscience topic my trainees and I have worked on over the past eight years: it is the problem of identifying interactions among neural populations from large-scale electrophysiological recordings. I will describe statistically natural approaches we have used to document interactions among brain areas based on neural spike trains (using latent variable point process models) and oscillating field potentials (by defining an exponential family on a multidimensional torus). I will also highlight some of the high-level lessons I've learned about the nature of statistical inference in science, which suggest ways we can continue to improve the scientific process.

Contact: Danny Forger