Sven Schreiber schrieb: > Artur T. schrieb: > > >> For some data I get the following message which I can't interpret >> adequately: >> >> ----output---- >> BreitungCandelonTest(emplrate,capacity,conditioning,lagorder,points,siglevel >> \ >> ) >> Date strings inconsistent >> error in new starting obs >> error in function BreitungCandelonTest >> > smpl 1 numoffreqs >> >> > > First, after looking at the manual I'm not even sure anymore that the > syntax "smpl startobs endobs" is supposed to support simple integer > observation numbers for time series. That case doesn't seem to be > explicitly mentioned. (But of course, it works, at least in the examples > that I tried.) > > Second, I don't really know what's happening. What's your dataset, your > data range, and your sample selection when you call the function? > Related to that, some speculation: Maybe your sample doesn't start at > the first available obs in the dataset, so when the function tries to > set the startobs to 1, it's illegal for it to do so. If that were the > case, I'm not sure whether it's a gretl bug or a bug in my function. > (Meaning, I'm not sure whether it should be considered illegal, or > whether the smpl command inside a function should be evaluated relative > to the current sample.) > > thanks for testing! > > -sven > > > _______________________________________________ > Gretl-devel mailing list > Gretl-devel(a)lists.wfu.edu > http://lists.wfu.edu/mailman/listinfo/gretl-devel > It seems that the error is caused by a change in the sample size. Using the full range works fine (tested on other data sets) but as soon as I change the sample start arbitrarily the error occurs again. Only changing the sample end (leaving the start at its first observation) does not lead to any error.
Artur
