11:12 a.m.
I know there are functions to compute the mean, median, minimum, maximum and standard
deviation for a series. I also know that using the summary command, skewness and
excess-kurtosis are also computed. Is there an easy way to capture these last two
statistics (I need them for further processing)? Of course, I could write a short function
to do this, but as they are already available in Gretl in the summary command…
Thanks,
Jan Annaert
UNIVERSITEITANTWERPEN | Faculty of Applied Economics (TEW) | Dept. Accounting &
Finance
Room S.B.335 | Prinsstraat 13 | B-2000 Antwerp | Belgium
Phone +32 32654163 |Fax +32 32654064
12:50 p.m.
On Fri, 27 May 2011, Annaert Jan wrote:
I know there are functions to compute the mean, median, minimum,
maximum
and standard deviation for a series. I also know that using the summary
command, skewness and excess-kurtosis are also computed. Is there an
easy way to capture these last two statistics (I need them for further
processing)? Of course, I could write a short function to do this, but
as they are already available in Gretl in the summary command…
Not a bad idea, in fact. I'll see what I can do in the next few days.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
r.lucchetti(a)univpm.it
http://www.econ.univpm.it/lucchetti
6:11 a.m.
On Fri, 27 May 2011, Riccardo (Jack) Lucchetti wrote:
On Fri, 27 May 2011, Annaert Jan wrote:
> I know there are functions to compute the mean, median, minimum, maximum
> and standard deviation for a series. I also know that using the summary
> command, skewness and excess-kurtosis are also computed. Is there an easy
> way to capture these last two statistics (I need them for further
> processing)? Of course, I could write a short function to do this, but as
> they are already available in Gretl in the summary command…
Not a bad idea, in fact. I'll see what I can do in the next few days.
Two new functions, skewness() and kurtosis(), are now in CVS. As soon as
Allin approves them, I'll write the documentation.
I had also thought of adding one more function, but I'm not certain it
would be a good thing, so before I do, I'd like to hear the community's
take: my idea was to write a function which takes a series, or a list, as
argument and outputs a 4-column matrix with mean, sd, skewness and excess
kurtosis.
Pros: nice to have.
Cons: one more reserved word in the namespace for something that is rather
trivial to do via a short script.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
r.lucchetti(a)univpm.it
http://www.econ.univpm.it/lucchetti
9:12 a.m.
On 29-05-2011, at 12:11, Riccardo (Jack) Lucchetti wrote:
......
Two new functions, skewness() and kurtosis(), are now in CVS. As soon as Allin approves
them, I'll write the documentation.
I had also thought of adding one more function, but I'm not certain it would be a
good thing, so before I do, I'd like to hear the community's take: my idea was to
write a function which takes a series, or a list, as argument and outputs a 4-column
matrix with mean, sd, skewness and excess kurtosis.
Pros: nice to have.
Cons: one more reserved word in the namespace for something that is rather trivial to do
via a short script.
Put it in a function package?
Berend
3:26 a.m.
Thanks for the quick reply.
I certainly back the idea to have such a function package. It will make life easier for
many of us.
Jan
-----Original Message-----
From: Berend Hasselman [mailto:bhh@xs4all.nl]
Sent: 29 May 2011 15:12
To: r.lucchetti(a)univpm.it; Gretl list
Subject: Re: [Gretl-users] skewness and kurtosis
On 29-05-2011, at 12:11, Riccardo (Jack) Lucchetti wrote:
......
Two new functions, skewness() and kurtosis(), are now in CVS. As soon as Allin approves
them, I'll write the documentation.
I had also thought of adding one more function, but I'm not certain it would be a
good thing, so before I do, I'd like to hear the community's take: my idea was to
write a function which takes a series, or a list, as argument and outputs a 4-column
matrix with mean, sd, skewness and excess kurtosis.
Pros: nice to have.
Cons: one more reserved word in the namespace for something that is rather trivial to do
via a short script.
Put it in a function package?
Berend
4:03 a.m.
*
It will also be very good if another column added for median.
Thank you.
*Md. Mohan Uddin
____________________________________________________________________________
Assistant Professor (on study leave) | School of Business | United
International University
Dhaka, Bangladesh | www.uiu.ac.bd
On Mon, May 30, 2011 at 3:26 PM, Annaert Jan <jan.annaert(a)ua.ac.be> wrote:
Thanks for the quick reply.
I certainly back the idea to have such a function package. It will make
life easier for many of us.
Jan
-----Original Message-----
From: Berend Hasselman [mailto:bhh@xs4all.nl]
Sent: 29 May 2011 15:12
To: r.lucchetti(a)univpm.it; Gretl list
Subject: Re: [Gretl-users] skewness and kurtosis
On 29-05-2011, at 12:11, Riccardo (Jack) Lucchetti wrote:
> ......
> Two new functions, skewness() and kurtosis(), are now in CVS. As soon as
Allin approves them, I'll write the documentation.
>
> I had also thought of adding one more function, but I'm not certain it
would be a good thing, so before I do, I'd like to hear the community's
take: my idea was to write a function which takes a series, or a list, as
argument and outputs a 4-column matrix with mean, sd, skewness and excess
kurtosis.
>
> Pros: nice to have.
> Cons: one more reserved word in the namespace for something that is
rather trivial to do via a short script.
Put it in a function package?
Berend
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
1:16 p.m.
Am 29.05.2011 12:11, schrieb Riccardo (Jack) Lucchetti:
On Fri, 27 May 2011, Riccardo (Jack) Lucchetti wrote:
> On Fri, 27 May 2011, Annaert Jan wrote:
>
>> I know there are functions to compute the mean, median, minimum,
>> maximum and standard deviation for a series. I also know that using
>> the summary command, skewness and excess-kurtosis are also computed.
>> Is there an easy way to capture these last two statistics (I need
>> them for further processing)? Of course, I could write a short
>> function to do this, but as they are already available in Gretl in
>> the summary command…
>
> Not a bad idea, in fact. I'll see what I can do in the next few days.
Two new functions, skewness() and kurtosis(), are now in CVS. As soon as
Allin approves them, I'll write the documentation.
I had also thought of adding one more function, but I'm not certain it
would be a good thing, so before I do, I'd like to hear the community's
take: my idea was to write a function which takes a series, or a list,
as argument and outputs a 4-column matrix with mean, sd, skewness and
excess kurtosis.
Pros: nice to have.
Cons: one more reserved word in the namespace for something that is
rather trivial to do via a short script.
Is there a compelling use case?
-sven
1:53 p.m.
Dear Gretl Community,
I think we could just use an option flag in the "summary" command (like we
already have):
*summary --matrix="matrix name"*
So (in my humble opinion) I don't think a function for this task is
necessary.
Best regards,
Henrique
2011/5/29 Sven Schreiber <svetosch(a)gmx.net>
Am 29.05.2011 12:11, schrieb Riccardo (Jack) Lucchetti:
> On Fri, 27 May 2011, Riccardo (Jack) Lucchetti wrote:
>
>> On Fri, 27 May 2011, Annaert Jan wrote:
>>
>>> I know there are functions to compute the mean, median, minimum,
>>> maximum and standard deviation for a series. I also know that using
>>> the summary command, skewness and excess-kurtosis are also computed.
>>> Is there an easy way to capture these last two statistics (I need
>>> them for further processing)? Of course, I could write a short
>>> function to do this, but as they are already available in Gretl in
>>> the summary command…
>>
>> Not a bad idea, in fact. I'll see what I can do in the next few days.
>
> Two new functions, skewness() and kurtosis(), are now in CVS. As soon as
> Allin approves them, I'll write the documentation.
>
> I had also thought of adding one more function, but I'm not certain it
> would be a good thing, so before I do, I'd like to hear the community's
> take: my idea was to write a function which takes a series, or a list,
> as argument and outputs a 4-column matrix with mean, sd, skewness and
> excess kurtosis.
>
> Pros: nice to have.
> Cons: one more reserved word in the namespace for something that is
> rather trivial to do via a short script.
>
Is there a compelling use case?
-sven
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
--
*Henrique C. de Andrade*
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
www.ufrgs.br/ppge
4:56 a.m.
Am 30.05.2011 10:21, schrieb a.bala:
Le 29/05/2011 18:53, Henrique Andrade a écrit :
> I think we could just use an option flag in the "summary" command
> (like we already have):
> *summary --matrix="matrix name"*
Why not? I find this option more useful and suggestive than a function
package.
Just to be clear: There are the new (not-yet-approved) functions
skewness() and kurtosis(). The function package would bind these and
other functions together, essentially adding another API to those
functions.
IMO functions and commands serve different purposes, there is no real
competition between them and they are not substitutes.
I don't have anything against additional function packages, but I would
be against adding this to gretl (=its namespace) by default, it's just
redundant.
(BTW jack: is this excess kurtosis or not? If it is, I would be in favor
of a name change. Also, while I like the explicit names [up to 8
characters], I don't understand why at the time "dynpanel" was
considered too long, but "skewness" and "kurtosis" are not :-)
thanks,
sven
5:37 a.m.
On Mon, 30 May 2011, Sven Schreiber wrote:
Am 30.05.2011 10:21, schrieb a.bala:
> Le 29/05/2011 18:53, Henrique Andrade a écrit :
>> I think we could just use an option flag in the "summary" command
>> (like we already have):
>> *summary --matrix="matrix name"*
> Why not? I find this option more useful and suggestive than a function
> package.
>
Just to be clear: There are the new (not-yet-approved) functions
skewness() and kurtosis(). The function package would bind these and
other functions together, essentially adding another API to those
functions.
IMO functions and commands serve different purposes, there is no real
competition between them and they are not substitutes.
I don't have anything against additional function packages, but I would
be against adding this to gretl (=its namespace) by default, it's just
redundant.
I agree. Besides, it's not quite clear to me how the proposed package is
meant to be used. I mean: is it meant as a GUI interface to produce a
matrix out of a list? Ok, and then, once the matrix is created, what would
you do with it? Alternatively, if intended usage is mainly though a
script, do we really need a function package for something like this?
<script>
function matrix moments(list X)
scalar k = nelem(X)
ret = zeros(k, 4)
j = 1
loop foreach i X --quiet
ret[j, 1] = mean(X.$i)
ret[j, 2] = sd(X.$i)
ret[j, 3] = skewness(X.$i)
ret[j, 4] = kurtosis(X.$i)
j++
end loop
return ret
end function
# ---- example ---------------------------
open mroz87 --quiet
list X = 4 5 6
summary X
M = moments(X)
print M
</script>
(BTW jack: is this excess kurtosis or not? If it is, I would be in
favor
of a name change.
It is, for compatibility with the output of "summary", but of course, this
is easy to change if we so decide.
Also, while I like the explicit names [up to 8 characters], I
don't
understand why at the time "dynpanel" was considered too long, but
"skewness" and "kurtosis" are not :-)
You have a point. But then, what? "sk"? "skew"? "kurt"?
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
r.lucchetti(a)univpm.it
http://www.econ.univpm.it/lucchetti
2:50 a.m.
New subject: freq command
In script mode, the freq command does not produce the graph that is shown in the
interactive mode. However, in some cases it may be useful to have this feature as well in
script mode. Is it difficult to add an --output=display option to the command similar as
in the gnuplot command?
Jan Annaert
4:11 a.m.
New subject: freq command
Le 07/10/2011 07:50, Annaert Jan a écrit :
In script mode, the freq command does not produce the graph that is
shown in the interactive mode. However, in some cases it may be useful
to have this feature as well in script mode. Is it difficult to add an
--output=display option to the command similar as in the gnuplot command?
Basically, adding the --output flag into a script does produce the same
effect as in the comand line.
For example the following script will show on the screen 4 time series
plots
/open australia.gdt
loop foreach i PAU..IAU
gnuplot $i --output=display --time-series
endloop/
Best,
Artur
12:39 p.m.
New subject: freq command
On Fri, 7 Oct 2011, Annaert Jan wrote:
In script mode, the freq command does not produce the graph
that is shown in the interactive mode. However, in some
cases it may be useful to have this feature as well in
script mode. Is it difficult to add an --output=display
option to the command similar as in the gnuplot command?
The precise option "--output=display" doesn't really fit for
this context, but I've added an option --show-plot which
forces the display of the frequency plot when the "freq"
command is used in a script.
Allin Cottrell
12:57 p.m.
New subject: Weak Instrument test with TSLS
Dear All,
I'm applying the TSLS estimation method. In a regression with just one
endogenous regressor, the output shows an F-test(Weak Instrument test) for the First
Stage regression. Meanwhile, when I perform a similar regression with more than two
endogenous regressors, the output reveals an F-test statistics without any information on
whether it is that for the Weak Instrument test at First stage regression. I hope someone
must have come accross this in the past. The concern is to know how to interprete this
F-stats in the TSLS with more than two endogenous regressors. Do I inteprete it as the
weak instrument test or the second stage F-stats?
Thanks
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
1:41 p.m.
New subject: Weak Instrument test with TSLS
On Sat, 8 Oct 2011, Anutechia Asongu wrote:
I'm applying the TSLS estimation method. In a regression
with just one endogenous regressor, the output shows an
F-test(Weak Instrument test) for the First Stage regression.
Meanwhile, when I perform a similar regression with more
than two endogenous regressors, the output reveals an F-test
statistics without any information on whether it is that for
the Weak Instrument test at First stage regression. I hope
someone must have come accross this in the past. The concern
is to know how to interprete this F-stats in the TSLS with
more than two endogenous regressors. Do I inteprete it as
the weak instrument test or the second stage F-stats?
The F-test that is reported in the first block of information
under the table of coefficients is always simply the test for
the null that all the slopes are zero in the model printed
above. So in the case of TSLS it's a second-stage test.
As for the weak instruments test, the first-stage F-test is
not applicable when there are two or more endogenous
regressors. Gretl shows the Cragg-Donald minimum eigenvalue
and additional information based on the Stock-Yogo approach,
where these things can be computed.
www.nber.org/~myogo/papers/published/RothenbergCh5.pdf
Allin Cottrell
1:42 a.m.
New subject: summary by var
I came across strange behaviour of the summary command used with the --by option. When I
use it on a sample less than the full range and the byvar is a monthly dummy variable
(generated using the GUI), I do get the summary statistics for each category of the dummy
variable, but they are computed over the entire range.
Jan Annaert
11:41 a.m.
New subject: summary by var
On Wed, 26 Oct 2011, Annaert Jan wrote:
I came across strange behaviour of the summary command used
with the --by option. When I use it on a sample less than
the full range and the byvar is a monthly dummy variable
(generated using the GUI), I do get the summary statistics
for each category of the dummy variable, but they are
computed over the entire range.
OK, I see what you mean: the respective samples that are used
for the summary statistics are entirely determined by the
"byvar = value" criterion, and the incoming sample range is
ignored. This is now fixed in CVS and snapshots.
Allin Cottrell
4727
days inactive
4879
days old
18 comments
10 participants
participants (10)
-
a.bala -
Allin Cottrell -
Annaert Jan -
Anutechia Asongu -
artur bala
-
Berend Hasselman -
Henrique Andrade -
Md. Mohan Uddin -
Riccardo (Jack) Lucchetti -
Sven Schreiber