Hello,
I wanted to clarify the result of running gltsym and the difference between the following two scenarios:
1) -gltsym 'SYM: stim1 stim2' -glt_label 1 FullF -fout -tout -rout -bucket 3D-output
and
2) -gltsym 'SYM: stim1 \ stim2' -glt_label 1 FullF -fout -tout -rout -bucket 3D-output
In scenario 1, I get a corresponding coefficent, R^2, and t value for the combination (adding the coefficents of both stim1 and stim2) in the bucket output. The FullF_GLT t-stat is equal to the square root of the FullF_GLT F-stat. But the R^2 does not equal the Full R^2 provided in the output by default, and neither do the FullF_GLT_Fstat and Full_Fstat.
In scenario 2, the default full R^2 value and the glt R^2 equal each other. Also, I get separate glt's t-vaules and coefficents for stim1 and stim2. Its basically duplicate output, with 2 sets of the same full F, R^2, coefficents and t-values.
What accounts for the difference? Essentially, we want to obtain a Full F, parameter estimate and corresponding t-value for the contribution of both stim1 and stim2. Scenario 1 appears to be what we want, no?
Michael