AUTHOR=Bzdok Danilo 

TITLE=Classical Statistics and Statistical Learning in Imaging Neuroscience

JOURNAL=Frontiers in Neuroscience

VOLUME=11

YEAR=2017

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2017.00543

DOI=10.3389/fnins.2017.00543

ISSN=1662-453X

ABSTRACT=<p>Brain-imaging research has predominantly generated insight by means of classical statistics, including regression-type analyses and null-hypothesis testing using <italic>t</italic>-test and ANOVA. Throughout recent years, statistical learning methods enjoy increasing popularity especially for applications in rich and complex data, including cross-validated out-of-sample prediction using pattern classification and sparsity-inducing regression. This concept paper discusses the implications of inferential justifications and algorithmic methodologies in common data analysis scenarios in neuroimaging. It is retraced how classical statistics and statistical learning originated from different historical contexts, build on different theoretical foundations, make different assumptions, and evaluate different outcome metrics to permit differently nuanced conclusions. The present considerations should help reduce current confusion between model-driven classical hypothesis testing and data-driven learning algorithms for investigating the brain with imaging techniques.</p>