Marcin B. has been in touch with me about providing an accessor or
function such that you could retrieve ACF/PACF values for further
analysis, and I thought I'd bring this issue to the list.
Marcin originally requested an accessor, $corrgm, and I replied by
suggesting a function, acf(y, p) [y = series, p = max lag] which
would return a column vector. The correspondence then continued
as below. Comments welcome.
On Sun, 25 Jan 2009, Marcin B�^Bażejowski wrote:
> I was rather thinking about pacf() function (as a tool for
> determining order of autoregressive of given proces) and my
> thoughts was like thist (but it's only suggestion):
> $corrgm(m,n), where "m" is a order of function and "n" is a
> value of function (acf, pacf and so on).
In gretl's syntax, $foo is used strictly as an accessor for a
previously calculated result. So my thinking is that $corrgm
would have to retrieve the result from a previous "corrgm" command
(presumably, in the form of a vector of values).
This could work, but my alternative thought was to provide a
function acf() -- or corrgm(), the name doesn't matter much --
that works in a "stand-alone" manner to provide an acf vector.
This seemed a little more "natural" to me than using an accessor.
Now I take your point that one might also want the partial
autocorrelations, or for that matter the cross-correlogram of two
variables. We could do this by providing three functions, e.g.,
xcf(x, y, p)
where x and y are series and p is the maximum lag. It would be
possible to combine acf and pacf into one function by using a
third boolean parameter to distinguish the cases -- or, I suppose,
we could have a corrgm() function with returns a p x 2 matrix with
the ACF in column 1 and the PACF in column 2. I'm not sure which
of these options is best.
I'm the Brazilian Portuguese translator of gretl (together with
Hélio and Raquel), but I would like to help the gretl development in
other manners. Speaking in a more specific way: I would like to help
to improve the Mac OS/X version. How could I do this? Well, I think I
(1) Compile and make the dmg file of the current snapshots;
(2) Help to develop a X11 independent version of Mac OS/X gretl;
(3) Submit gretl to Apple's downloads homepage (and I also could
manage this, updating the download link whenever it is necessary).
But to achieve these aims I have two problems: (1) I'm not a Mac
expert (neither programmer expert); and (2) I'm a Ph.D. student, wich
means that I don't have a lot of time. I think, if you could help me,
I can handle the problem "number 1". And the problem "number 2" can be
solved by myself (I just need to rearrange my "study time".
I'll really apreciate to help gretl development!
Henrique C. de Andrade
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
just wanted to tell you that the new extended graphics handling is great
and very useful!
The same goes for the (not quite as new) cointegration/VECM enhancements
like testing and estimating restricted VECMs. Since it was introduced in
gretl this is the first time I'm using it for real work and it's very
nice that I don't have to switch to Pcgive or Jmulti. (I had a crash
with a certain constellation of restrictions, but those were quite many
restrictions and I can't reproduce them now.)
I encountered the following problem when specifying a VECM with
I wanted to specify x(-1) as a restricted exogenous variable. It turned
out to be not so easy to get the lag in there instead of just the
contemporaneous value; adding the lag of x to the dataset doesn't help,
because the lags don't show up in the VECM specification dialog. So I
had to manually create an auxiliary variable holding the lag of x.
Given that the VAR specification dialog has a great interface for
choosing the lags of exogenous variables, wouldn't it be natural to have
the same thing in the VECM window?
And while we're (or I'm) at it, couldn't this flexible approach for
choosing lags also be extended to endogenous variables?