Thanks a lot, Riccardo,

This is a very nice script.

But I'have a still a small doubt, about z-statistics and p-values computed.
The script gives me the bootstraped b and standard deviation, this is clear.
But the script provides a z statistics and its associated p-values.
Are they computed from this bootstraped beta and sd values in a clasic manner.? That is, calculating z ratio as usual and contrasting against normal.
Because I have seen that in many textbook the bootstraped z or t ratio is computed counting how many times the z or t statistic exceeds the baseline z or t gives us the true original estimate OLS. It is true?

Thanks a lot and best regards

José Perles

2013/5/29 Riccardo (Jack) Lucchetti <r.lucchetti@univpm.it>

On Wed, 29 May 2013, JOSE FRANCISCO PERLES RIBES wrote:

Of the options available in this menu and the information in Gretl guide, it
seems clear that this procedure is a "residual bootstrap" where the matrix of
regressors X is treated as fixed.

This is correct.

Is there any way by GUI option to do a "bootstrap case" where the regressors X are treated as "random"?.

Not yet. Is the algorithm you have in mind something like this?

<hansl>
function void randboot(series y, list X, scalar rep)
matrix DATA = { y || X }
k = nelem(X)
b = zeros(k, rep)
loop i=1..rep --quiet
Z = resample(DATA)
b[,i] = mols(Z[,1], Z[,2:])
end loop

cs = (meanc(b') | sdc(b'))'
pn = varname(X)

modprint cs pn
end function

open galton.gdt
list X = const parent
ols child X
randboot(child, X, 1000)
</hansl>

-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)

Università Politecnica delle Marche
(formerly known as Università di Ancona)

r.lucchetti@univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users