[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: lack-of-fit-test (maxr2)
As its help indicates, -maxr2- (STB-9; 1992; Richard
Goldstein) is to be run after -fit-. Therefore
run -fit-, not -regress-, before attempting to use this
-fit- is an out-of-date sibling of -regress-. That
said, the one experiment I did indicates that -maxr2-
is still usable given a prior -fit-.
> I tried to run the maxr2 subroutine in Stata SE 8.2 after the
> regress command in order to check lack-of-fit in a linear
> multiple regression as it is mentioned in
> Draper/Smith, Applied regression analysis.
> But unfortunately I got an error message:
> last estimates not found.
> I would be glad about any hint what to do?
* For searches and help try: