Introduction to logistic regression

TL;DR

This paper introduces a logistic regression framework for brain imaging analysis that localizes network differences without relying on traditional p-value based hypothesis testing, avoiding distributional assumptions.

Contribution

It presents a novel application of logistic regression at the edge level in brain networks, bypassing the need for preselected features and p-value computations.

Findings

Enables localization of brain network differences without p-values.

Operates directly at the edge level without feature preselection.

Provides an alternative to traditional multiple comparison corrections.

Abstract

For random field theory based multiple comparison corrections In brain imaging, it is often necessary to compute the distribution of the supremum of a random field. Unfortunately, computing the distribution of the supremum of the random field is not easy and requires satisfying many distributional assumptions that may not be true in real data. Thus, there is a need to come up with a different framework that does not use the traditional statistical hypothesis testing paradigm that requires to compute p-values. With this as a motivation, we can use a different approach called the logistic regression that does not require computing the p-value and still be able to localize the regions of brain network differences. Unlike other discriminant and classification techniques that tried to classify preselected feature vectors, the method here does not require any preselected feature vectors and performs the classification at each edge level.