Olaf Dimigen
Olaf Dimigen
`uf_checkmodelfit` does not work with `glmnet` due to extra variablename "glm-DC correction" (Found this bug in my notes, added it here just as a future todo list point.)
In M/EEG papers, it is common to report the number and/or percentage of rejected bad epochs (e.g. containing voltages exceeding peak-to-peak criteria) per condition. There are not yet standards on...
Minor issue: Example model: `{y ~ 1, y ~ 1 + cat(somefactor) + somepredictor}` For the (first) intercept-only (sub)model, the screen output for uf_addmarginal() claims that the intercept is added...
Do we have any experience with that? Produces error: Error using classreg.regr.FormulaProcessor>parseStr (line 663) Unable to understand the character vector 'response ~1+cat(myfactor)*spl(mysplinepredictor,5)+mylinearcovariate'.
Spline predictor topographies otherwise difficult to interpret (since intercept somewhere in the "middle")