> This is the approach that SPM always takes, and it doesn't seem to cause trouble when a model is just the interaction
> of several variables (quantitative or factorial), corresponding to an R model formula of (IIUC) `y ~ factor1*factor2`.
That's just an interface issue, and the internal pseudo-inverse approach works with the same mechanism as the other coding strategies. In terms of testing the special hypothesis
b_1 = b_2 = ... = b_n = 0
as far as I can tell, there is no magic wand when there are other variables involved regardless the coding method.
Gang