Stefan Appelhoff

Fine with me as well :+1:

I think you are right with the assessment that "it won't matter" in most cases, and I think for my data presently it also doesn't matter too much. However, I...

> This is a pretty easy operation (almost/possibly a one-liner) to do on the observed clusters after the fact, though. So I'd rather not add a parameter for this, but...

> This is not the case for your example according to a standard lattice adjacency, there are four clusters: I see - but does that make my point invalid? :slightly_smiling_face:...

The fieldtrip parameter description says: ```python cfg.minnbchan = 2; % minimum number of neighborhood channels that is % required for a selected sample to be included % in the clustering...

> Should there even be 1 cluster? **I think no**, since the singletons should be culled by the algorithm... agreed > As far as the naming goes, we could consider...

I just got a (maybe naive) question: When I supply 3D data (channels x times x frequencies) ... is the clustering also happening over frequencies? E.g., a cluster because at...

> Yes. thanks! Regarding this I also just found this [example](https://mne.tools/stable/auto_tutorials/stats-sensor-space/40_cluster_1samp_time_freq.html?highlight=adjacency#define-adjacency-for-statistics), where on top of the sensor adjacency (via [mne.channels.find_ch_adjacency](https://mne.tools/stable/generated/mne.channels.find_ch_adjacency.html#mne.channels.find_ch_adjacency)), a "lattice" (whatever that is) adjacency is **added** (via [mne.stats.combine_adjacency](https://mne.tools/stable/generated/mne.stats.combine_adjacency.html#mne.stats.combine_adjacency))...

> I'm not sure what will happen then, but if you are clustering in channels, time and space in mne then you should use combine_adjacency Interesting! Looking at this [example](https://mne.tools/stable/auto_tutorials/stats-sensor-space/75_cluster_ftest_spatiotemporal.html#find-the-fieldtrip-neighbor-definition-to-setup-sensor-adjacency)...

To me this sounds like one PR that adds this feature, as Eric described in https://github.com/mne-tools/mne-python/issues/10604#issuecomment-1119722416 (although that comment only describes time and space, and we should also implement this...