Hi all,
Have got three variables that are highly correlated which I'll like to
summarise as an index using the first Principal Component(PC) in the PCA. However, I
don't know how to extract data of the first PC.
Please could someone help?
--- On Mon, 11/1/10, Eloy A. Fisher Hogan <eloyfisher(a)hotmail.com> wrote:
From: Eloy A. Fisher Hogan <eloyfisher(a)hotmail.com>
Subject: Re: [Gretl-users] Recursive processes:
To: gretl-users(a)lists.wfu.edu
Date: Monday, November 1, 2010, 3:20 AM
Thanks Allin!
EF
Date: Sun, 31 Oct 2010 22:05:05 -0400
From: cottrell(a)wfu.edu
To: gretl-users(a)lists.wfu.edu
Subject: Re: [Gretl-users] Recursive processes:
On Sun, 31 Oct 2010, Eloy A. Fisher Hogan wrote:
> Hello everyone, I trying to migrate from Eviews to GRETL so
> perhaps this is noob question - how can we state recursive
> processes in GRETL?
> I generate the nulldata 200 and create a random et using
> randgen, I try to use the ARMA functionality but it doesn't
> recognize the 0.8 coefficient, when I try to estimate yt I run
> into problems. In E-views the code is:
>
> smpl @first @last
> series e=nrnd
> smpl @first @first
> series y = 0
> smpl @first+1 @last
> series y = .8*y(-1)+e
It's very similar in gretl:
nulldata 200
series e = normal()
series y = 0
y = .8*y(-1) + e
Alternatively, there's the filter() function.
Allin Cottrell
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
-----Inline Attachment Follows-----
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users