New: a case for group analysis that doesn't need multiple comparison correction

Here is some new work by Gang (again??) on analyzing data sets without the need for pesky multiple comparisons corrections:

How to Deal with Multiplicity in Neuroimaging? A Case for Global Calibration

And definitely worth checking out for anyone with a matrix appearing in their analyses/results.

Is this implemented in AFNI?

Yes. The programs RBA, MBA and 3dISC use Bayesian multilevel (BML) modeling.

For the MBA program for matrix-based analysis:
Chen G, Burkner P-C, Taylor PA, Li Z, Yin L, Glen DR, Kinnison J, Cox RW, Pessoa L (2019). An Integrative Approach to Matrix-Based Analyses in Neuroimaging. Human Brain Mapping (in press) doi:10.1101/459545

For a Bayesian Multilevel (BML) modeling approach with the RBA program:
Chen G, Xiao Y, Taylor PA, Rajendra JK, Riggins T, Geng F, Redcay E, Cox RW (2019). Handling Multiplicity in Neuroimaging Through Bayesian Lenses with Multilevel Modeling. Neuroinformatics. 17(4):515-545. doi:10.1007/s12021-018-9409-6

For an ROI-based approach through Bayesian multilevel (BML) modeling to ISC (inter-subject correlation) and naturalistic FMRI:
Chen G, PA Taylor, Qu X, Molfese PJ, Bandettini PA, Cox RW, Finn ES (2020). Untangling the Relatedness among Correlations, Part III: Inter-Subject Correlation Analysis through Bayesian Multilevel Modeling for Naturalistic Scanning. NeuroImage 216:116474. doi:10.1016/j.neuroimage.2019.116474

And you can see a broader list of papers and specific tools here: