Henrique Andrade a écrit :
>
> matrix R = zeros(12,1)
>
> loop i=6..12
> R_$i = r[$i,1] + r[$i-1,2]+ r[$i-2,3]+ r[$i-3,4]+ r[$i-4,5]+ r[$i-5,6]
> R[i] = R_$i
> end loop
>
>
Hi Henrique,
Well, what do you think about the following general form :
matrix R = zeros(dim1,dim2)# In your e
On Sat, 17 Apr 2010, Henrique Andrade wrote:
> I'd attached a .pdf file into this e-mail to show you a little bit better
> what exactly I need.
On that basis, here's an example:
matrix r = mshape(seq(1,144),12,12)
print r
scalar m = 7 # number of values to compute
scalar n = 6 # number of ele
On Mon, 19 Apr 2010, yinung at Gmail wrote:
> I could find the formula explaining how to calculate McFadden R-squared in
> the gretl user's guide.
> I tried to replicate it in Probit model but I fail to get the same value. Is
> anything wrong with my calculation as follows.
We use the formula yo
Dear Artur and Allin,
Thank you so much for your invaluable help. Now everything is working
really fine! With the use of the Gretl scripting language I'm going to save
a lot of time (these tasks are part of my PhD thesis).
Best regards,
Henrique
2010/4/18 Allin Cottrell
>
> On Sat, 17 Apr 2010
On Mon, 19 Apr 2010, yinung at Gmail wrote:
> Thanks, Allin
> 2010/4/19 Allin Cottrell
> >
> > If I run your script as modified I get a "test" value of
> > 1.665e-16, which doesn't seem like a problem. What are you seeing?
> >
> > Allin
> > ___
> >
>
yinung at Gmail schrieb:
>
>
> This is what I got (the script is attached in the bottom of this mail).
> The difference is quiet large. test = -0.108229
> I use gretl for windows build date 2010-03-26
>
It seems to me you're asking in your script for the wrong $rsq (you're
asking one model too l
