Re: [Gretl-devel] [Gretl-users] Loop recursion: Speed comparison with Matlab
Am 24.10.2017 um 17:12 schrieb Artur Tarassow:
Am 24.10.2017 um 17:08 schrieb Sven Schreiber:
> I guess it would be useful if Stefano could weigh in. The
question is,
> is the new SB() code equivalent to the old SBslow() code in terms of
> output, apart from any speed concerns.
I did the comparison, see the commented example 2 in the sample. The
differences are marginal.
Maybe, maybe not. With a quite large nboot=49999 I get for the
"lower-left" interval limits:
SBslow:
Lower limits 3.02
Upper limits 5.78
SB
Lower limits 3.11
Upper limits 5.72
This is of course not a dramatic difference, but with 50K iterations I'm
not sure we should be seeing this.
thanks,
sven