ARIMASel (Automatic ARIMA selection)

For questions about EViews Add-ins available from the EViews Add-ins webpage. Note each add-in available on our webpage will have its own individual thread.

Moderators: EViews Gareth, EViews Moderator, EViews Esther

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Mon May 16, 2011 8:09 am

Ah, I didn't follow that you were using a single endogenous variable.

I've just run a few tests, and I always get identical results in my data. Could you provide an example where you don't?
Follow us on Twitter @IHSEViews

ECaster
Posts: 2
Joined: Tue May 24, 2011 1:57 am

Re: ARIMASel (Automatic ARIMA selection)

Postby ECaster » Tue May 24, 2011 2:12 am

Hey,

I have a series containing about 65000 numbers and I tried to run the armasel program for this series. However, every time I get the error message "Armasel is not a valid view for S"
(S is the series).

Additionally, I attempted to run the program for a series reduced to 3000 observations only. Again, I get the same error message.

Any suggestions?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Tue May 24, 2011 7:47 am

Do you have the add-in installed?
Follow us on Twitter @IHSEViews

ECaster
Posts: 2
Joined: Tue May 24, 2011 1:57 am

Re: ARIMASel (Automatic ARIMA selection)

Postby ECaster » Tue May 24, 2011 7:58 am

yea,

I actually tried again with another series and it worked. I have to try again with the other series. Probably, I did something wrong the first time.

Thanks anyway!


Further, I have another question. If the program chooses AR(10)MA(10), it means that the series is hardly predictably, am I right?

miksterz1
Posts: 33
Joined: Fri May 20, 2011 5:20 am

Re: ARIMASel (Automatic ARIMA selection)

Postby miksterz1 » Tue Jun 07, 2011 12:56 pm

Gareth,

I would like the ARIMAsel function to store the selected equation when it estimates it. I added the line of code you suggested to another poster but it doesn't see to do the trick.

Code: Select all

 string chosenstr = {%eqname}.@spec


Any idea what the issue could be? Or is that not quite what the above is supposed to do?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Tue Jun 07, 2011 1:11 pm

That line will create a string object in your workfile containing the specification of the chosen equation. You can always then create your own equation with that specification.
Follow us on Twitter @IHSEViews

miksterz1
Posts: 33
Joined: Fri May 20, 2011 5:20 am

Re: ARIMASel (Automatic ARIMA selection)

Postby miksterz1 » Tue Aug 23, 2011 11:39 am

Gareth,

I am running ARIMAsel through 54 series. I would like to set up a program that runs ARIMAsel on all 54 series and then stores equation objects for each. Then I can use these for forecasting etc.

I'm not sure how to go from having a string with the best specification to having an equation be estimated using that specification (apart from doing it manually, of course)

Any help would be much appreciated

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Tue Aug 23, 2011 11:50 am

Assuming you have a string containing the specification called chosenstr:

Code: Select all

equation myeq.ls {chosenstr}
Follow us on Twitter @IHSEViews

miksterz1
Posts: 33
Joined: Fri May 20, 2011 5:20 am

Re: ARIMASel (Automatic ARIMA selection)

Postby miksterz1 » Tue Aug 23, 2011 12:30 pm

Thanks. It is now doing what I want it to but the string being saved looks like this:

_TEMPSER01 C MA(1)

Obviously there is no series called _TEMPSER01. Is there something I can alter in the program code for _TEMPSER01 to be the actual series name?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Tue Aug 23, 2011 1:10 pm

easiest thing to do is just to keep the series called _tempser01 in your workfile. To do this, simple remove the line that says:

Code: Select all

d {%temps}
Follow us on Twitter @IHSEViews

miksterz1
Posts: 33
Joined: Fri May 20, 2011 5:20 am

Re: ARIMASel (Automatic ARIMA selection)

Postby miksterz1 » Tue Aug 23, 2011 1:18 pm

Sorry, I meant suppose my series is called GDP, how can I have it be called GDP in the string as well instead of being assigned the temp name. This may sound trivial but I need to run a loop that estimates 54 equations based on the criteria chosen by ARIMAsel for each of 54 variables.

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Tue Aug 23, 2011 1:23 pm

Yeah, but the point is that you can't have GDP as the dependent variable (unless you have chosen a maximum differencing of 0), since the routine might have taken differences. The values in the series tempser01 will contain the differenced data, so you do actually want tempser01 to be the dependent variable.
Follow us on Twitter @IHSEViews

miksterz1
Posts: 33
Joined: Fri May 20, 2011 5:20 am

Re: ARIMASel (Automatic ARIMA selection)

Postby miksterz1 » Tue Aug 23, 2011 1:26 pm

But I'm using data that has been transformed the way I want and then setting diff=0 so that isn't an issue!

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12641
Joined: Tue Sep 16, 2008 5:38 pm

Re: ARIMASel (Automatic ARIMA selection)

Postby EViews Gareth » Tue Aug 23, 2011 1:47 pm

then you'll have to manipulate the string using the @w functions to remove the first word and replace it with the name of your variable.
Follow us on Twitter @IHSEViews

miksterz1
Posts: 33
Joined: Fri May 20, 2011 5:20 am

Re: ARIMASel (Automatic ARIMA selection)

Postby miksterz1 » Thu Aug 25, 2011 2:06 pm

Thanks for your help, Gareth. I've got it working now but something weird is happening. I'm running a look for 54 variables but it is stopping at the 19th one. The reason is no string seems to be getting created after the 19th series. I'm not sure why this is the case. My code follows. My 54 series are called c1,c2...,c54

Code: Select all

for !j = 1 to 54
c{!j}.arimasel(maxar=2,maxma=0,sar=12,sma=0,diff=0,crit="aic")
string c{!j}_chosen = chosenstr
string c{!j}_crit = @wdrop(c{!j}_chosen,"_TEMPSER01")
equation eq_c{!j}.ls c{!j} {c{!j}_crit}
next


Return to “Add-in Support”

Who is online

Users browsing this forum: No registered users and 12 guests