[Gretl-users] StrucBreak package (drawback)

Dear all, I would like to report a problem with the "StrucBreak" package. If I insert a dummy variable as a regressor, collinearity arises in (at least) one regime, and the estimation fails. I attach the following script to fix the problem. #--------------------------------------------------------- set verbose off include StrucBreak.gfn nulldata 60 setobs 4 2005:1 series y = normal() series d = obs > 30 ? 0 : normal() > 1 list Z = const d bundle m = SB_Setup(y, Z) SB_Global(&m) #--------------------------------------------------------- Cheers Giulio