10:52 a.m.
We now have a reasonably full implementation of Q-Q plots. Please
see the help for "qqplot" in current CVS for details.
CLI:
qqplot with one series argument: Q-Q against normal
qqplot with 2 series arguments: cross-plot of empirical quantiles
GUI:
/Variable/Normal Q-Q plot
/View/Graph specified vars/Q-Q plot
Options for normal Q-Q plot:
default: plot standardized data against N(0,1)
option --sample-stats: plot raw empirical quantiles against
N(\bar{x}, s^2)
option: --raw: empirical quantiles against N(0,1)
Allin.
11:58 a.m.
Em 6 de janeiro de 2010 Allin Cottrell <cottrell(a)wfu.edu> escreveu:
We now have a reasonably full implementation of Q-Q plots. Please
see the help for "qqplot" in current CVS for details.
Good!
CLI:
qqplot with one series argument: Q-Q against normal
qqplot with 2 series arguments: cross-plot of empirical quantiles
GUI:
/Variable/Normal Q-Q plot
/View/Graph specified vars/Q-Q plot
Suggestion: I think it would be good to put the Q-Q plot into "Model window"
to allow testing of the regression residuals (just like the normality test
we already have).
Best,
Henrique C. de Andrade
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
www.ufrgs.br/ppge
12:51 p.m.
On Wed, 6 Jan 2010, Henrique wrote:
Em 6 de janeiro de 2010 Allin Cottrell <cottrell(a)wfu.edu>
escreveu:
> We now have a reasonably full implementation of Q-Q plots.
> Please see the help for "qqplot" in current CVS for details.
Suggestion: I think it would be good to put the Q-Q plot into
"Model window" to allow testing of the regression residuals
(just like the normality test we already have).
OK, that's now added in CVS.
Allin.
8:46 p.m.
Thanks Allin!
2010/1/6 Allin Cottrell <cottrell(a)wfu.edu>
On Wed, 6 Jan 2010, Henrique wrote:
> Em 6 de janeiro de 2010 Allin Cottrell <cottrell(a)wfu.edu> escreveu:
>
> > We now have a reasonably full implementation of Q-Q plots.
> > Please see the help for "qqplot" in current CVS for details.
>
> Suggestion: I think it would be good to put the Q-Q plot into
> "Model window" to allow testing of the regression residuals
> (just like the normality test we already have).
OK, that's now added in CVS.
Allin.
_______________________________________________
Gretl-devel mailing list
Gretl-devel(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-devel
--
Henrique C. de Andrade
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
www.ufrgs.br/ppge
8:12 p.m.
Thanks for the QQs. I was just rewriting my class notes for this
semester, on box-plots and qq's.
Timing is great.
Peter
Allin Cottrell wrote:
On Wed, 6 Jan 2010, Henrique wrote:
> Em 6 de janeiro de 2010 Allin Cottrell <cottrell(a)wfu.edu> escreveu:
>
>
>> We now have a reasonably full implementation of Q-Q plots.
>> Please see the help for "qqplot" in current CVS for details.
>>
> Suggestion: I think it would be good to put the Q-Q plot into
> "Model window" to allow testing of the regression residuals
> (just like the normality test we already have).
>
OK, that's now added in CVS.
Allin.
_______________________________________________
Gretl-devel mailing list
Gretl-devel(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-devel
5427
days inactive
5429
days old
5 comments
3 participants
participants (3)
-
Allin Cottrell -
Henrique -
peter