Replicating Hafner and Herwartz (2006) VIRFs

Use this forum to post questions about syntax problems or general programming issues. Questions on implementing a particular aspect of econometrics should go in "Econometrics Issues" below.
OS27
Posts: 7
Joined: Tue Jul 18, 2017 8:29 pm

Replicating Hafner and Herwartz (2006) VIRFs

Unread post by OS27 »

Hello,

This is my first time using RATS so please excuse what I think is a very simple question. I am currently trying to follow the VIRF manual attached. Everything works up until the point where I enter:

Code: Select all

dec vect[series] sept92virf(3)
do i=1,3
set sept92virf(i) 1 nstep=0.0
I keep getting the error message:

## SX22. Expected Type INTEGER, Got REAL Instead
>>>>irf(i) 1 nstep=0.0<<<<

I am following the manual word by word so why may this be happening?
Attachments
GARCH Sample.pdf
(169.67 KiB) Downloaded 797 times
TomDoan
Posts: 7814
Joined: Wed Nov 01, 2006 4:36 pm

Re: Replicating Hafner and Herwartz (2006) VIRFs

Unread post by TomDoan »

You're missing the space before the =

https://estima.com/ratshelp/setinstruction.html
OS27
Posts: 7
Joined: Tue Jul 18, 2017 8:29 pm

Re: Replicating Hafner and Herwartz (2006) VIRFs

Unread post by OS27 »

Hello Tom,

Thank you for your prompt response. I have already tried putting a space but I am getting the same error:

Code: Select all

dec vect[series] sept92virf(3)
do i=1,3
set sept92virf(i) 1 nstep = 0.0
## SX22. Expected Type INTEGER, Got REAL Instead
>>>>t92virf(i) 1 nstep <<<<
The above is literally copied and pasted from the document.

Code: Select all

dec vect[series] sept92virf(3)
do i=1,3
set sept92virf(i) 1 nstep =0.0
## SX22. Expected Type INTEGER, Got REAL Instead
>>>>t92virf(i) 1 nstep <<<<
OS27
Posts: 7
Joined: Tue Jul 18, 2017 8:29 pm

Re: Replicating Hafner and Herwartz (2006) VIRFs

Unread post by OS27 »

Hi I am still unable to resolve this. Could anyone help please?
TomDoan
Posts: 7814
Joined: Wed Nov 01, 2006 4:36 pm

Re: Replicating Hafner and Herwartz (2006) VIRFs

Unread post by TomDoan »

First of all, the entire program is in the Paper Replications folder so you don't have to cut and paste out of a PDF (or worse, retype).

It looks like you might have done

compute nstep=400.

rather than

compute nstep=400

The first makes NSTEP a real which can't be used for numbering entries.
Post Reply