Hi Alessandro, Just FYI > I must create a new time series y(t), with 250 observations, resampling with > replacement the elements of x. I have used the command > > genr y = replace(x) Are you sure that's "replace" and not "resample" ? ;) > but gretl creates y(t) with 200 observations. That's normal. As long as the dataset "dimension" is of 200 observations, no series may contain more than 200 obs. > Can I create y with 250 > observations? You have to add more 50 observations but will not be worth of it : by resampling x, y series will still contains 200 obs taken from x and 50 obs labelled as NA (not available).

Le 10/09/2011 12:15, Sven Schreiber a écrit : > Yes, but he could do the resampling twice and take the first 200 obs > from the first series, and the final 50 obs from the second series, > and glue the parts together to get a 250-obs series. Is this what you mean Sven ? nulldata 200 series x = normal() # resampling twice series y1 = resample(x) series y2 = resample(x) # adding observations addobs 50 # stacking y2 to y1 loop i = 201..250 --quiet y1[i] = y2[i-200] endloop # here's the final series y series y = y1 delete y1 y2 print x y --byobs