Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: RE: ARIMA Order Selection


From   "Mostafa Baladi" <[email protected]>
To   <[email protected]>
Subject   st: RE: RE: ARIMA Order Selection
Date   Thu, 13 Dec 2007 10:18:20 -0600

Nick,

Thanks a lot for your attention and advice.  I re-phrased the question
in the hope of getting some response.  I am aware of a good deal of the
textbook and articles discussions on this issue.  My question is whether
STATA has any commands or options in some commands or something in the
interactive mode that allows us to pick the best ARIMA.  I am also
hoping to get some programming advice on how to start a loop in finding
the optimal model.

Once again I do thank you for your attention.

Mostafa



-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Nick Cox
Sent: Thursday, December 13, 2007 9:58 AM
To: [email protected]
Subject: st: RE: ARIMA Order Selection

Welcome to Stata and to Statalist. 

This is in fact the second version of a question you posted
yesterday. No one responded to that. 

Someone else may naturally want to reply for all I know, but for the
moment 
I have two pieces of advice to you and to others relatively new to the 
list. 

First, the FAQ includes specific advice on reposts. The main burden of
that 
advice is that whenever you don't get any replies it is best to try 
a very different kind of question. 

Second, very general questions like this get answered only with 
small probability. It is not so much that there are no experts who 
could tell you something worth your knowing; it is that very few 
people want to sit down and write a long tutorial on this subject, 
especially when a topic is the stuff of dozens of textbook chapters
and review articles. 


Nick
[email protected] 

Mostafa Baladi


I am very new to STATA and this is my first question posed to the group.
Sorry if it is not an exciting question or if it is too easy.  

I need to find the best ARIMA based on some criterion (log likelihood or
whatever) within a range of p and q.
Would anybody be nice enough to give some advice (no matter how general)
on this?

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index