Sven,
sorry for not coming back to you sooner.
Most likely one has to call it "does not respond" or "freeze"
Yesterday evening, I waited several hours for a response, in fact Gretl did not respond
after running all night.
Because this happened after the estimation process was finished (all matrices were created
and filled), the only thing missing to properly end the procedure was that Gretl returns
the script output with all the echos (which were not set to off). I did not expect that
producing a text output is more time consuming than estimating several quantile
regressions. It took Gretl approximately 10 minutes to create one matrix (497 rows, 1317
columns), which hold the weighted quantile estimates (> 3,000,000 quantile
regressions), which seems quite fast to me.
However, using the command "set echo off", does not lead to the very long
response time (or freeze).
I also tried to run a simpler script, that basically calculates for each individual and
each step an average of the weighted quantiles.
Again, not using the "set echo off" option, leads to a very long response time.
I terminated Gretl after an hour and rerun the script using the "set echo off",
which did not cause any response time.
I am not sure, if the explanation of my problem is clear enough.
Summarizing:
To me it seems Gretl has some response problems producing very long script outputs but
using "set echo off" seems to be sufficient to suppress this behavior (at least
for my problem).
Thank you very much for your patience and all your helpful comments.
Best,
Jan
-----Ursprüngliche Nachricht-----
Von: Plus.line MailSystem [mailto:cyrus@mailer.plusline.de] Im Auftrag von Sven Schreiber
Gesendet: Donnerstag, 7. Januar 2016 16:57
An: gretl-users(a)lists.wfu.edu
Betreff: Re: [Gretl-users] gretl crashes during quantile regression
Am 07.01.2016 um 07:07 schrieb Riccardo (Jack) Lucchetti:
On Thu, 7 Jan 2016, Jan Tille wrote:
[...]
The only piece of advice I have for you at this stage, is: try
reducing the size of your problem by cutting down the number of
individuals and/or the number of steps, if possible. If the problem
persists even with a much smaller combination, then the problem is
most likely with gretl and we'll be able to diagnose what the problem
is. If the problem goes away, perhaps the data you dropped contain some oddness.
I haven't read the entire thread, but just to be clear:
There doesn't seem to be a "crash" in the sense of gretl exiting
unexpectedly. (right?)
Furthermore, it could just be that gretl doesn't "respond" anymore because
it's busy crunching the numbers. (right?)
Or are we actually talking about a "freeze" in the sense that gretl will never
return to a normal state, even after waiting for a very long time (which could be hours,
days...)?
thanks,
sven
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users