Re: st: RE: Bug with dfuller?

[Mr Helder Zavale <h_zavale@yahoo.com>]

Thanks Martin for your clarification.

I should have used the following codes:

****
webuse air2, clear
dfuller air, regress lag(1)
regress D.air L.air LD.air
capture =0Adrop res_cattle
predict res_cattle, residuals
****

I want to look at the properties of the residuals from the regression used =
in the Dickey-Fuller test. As you mentioned, dfuller does not have a predic=
t-postestimation suite of commands. Therefore, I should have added the comm=
and  regress with the appropriate variables before the command predict.

Thanks,
Helder

---------------------------------------------------------------------------=
-------------------------------------------------
  Real integrity is doing the right thing, knowing that nobody's going to  =
   know whether you did it or not. =20
  Oprah Winfrey  =20
  -------------------------------------------------------------------------=
---------------------------------------------------
 =20
  Zavale, H=E9lder =20
UEM - FAEF


--- On Sat, 3/13/10, Martin Weiss <martin.weiss1@gmx.de> wrote:

From: Martin Weiss <martin.weiss1@gmx.de>
Subject: st: RE: Bug with dfuller?
To: statalist@hsphsun2.harvard.edu
Date: Saturday, March 13, 2010, 11:04 PM


<>
Which residuals do you want Stata to return? -dfuller- does not have seem t=
o
have a -predict- postestimation suite of commands. So I get "last estimates
not found":

****
webuse air2, clear
dfuller air, regress lag(1)
capture drop res_cattle
predict res_cattle, residuals
****



-dfuller- is an r-return command, so the fact that your code does run the
first time may be due to an earlier e-ereturn command having been run?


Martin


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Mr Helder Zavale
Sent: Samstag, 13. M=E4rz 2010 20:20
To: statalist@hsphsun2.harvard.edu
Subject: st: Bug with dfuller?

Dear Stata user,

I run dfuller command as follows

dfuller cattle, regress lag(1)
capture drop res_cattle
predict res_cattle, residuals
corrgram res_cattle

The first time I ran the above command lines, there was no problem. However=
=3D
, when I try to run them for the second time, I get the following message

capture drop res_cattle
. predict res_cattle, residuals
variable __000006 not found
r(111);

I am able to get the results of the Dickey-Fuller test but I not able to ge=
=3D
t the residuals from the regression. After exiting and re-opening Stata, th=
=3D
e command lines run with no problem for the first time, but then I get the =
=3D
same message when trying to run the command for the second time. I am using=
=3D
 Stata 11. Does anyone know what is going on?

Thanks,
Helder

---------------------------------------------------------------------------=
-
------------------------------------------------
=A0 Real integrity is doing the right thing, knowing that nobody's going to
know whether you did it or not.=20
=A0 Oprah Winfrey=A0=20
=20
---------------------------------------------------------------------------=
-
------------------------------------------------
=20
=A0 Zavale, H=3DE9lder=20
UEM - FAEF



*
*=A0=A0=A0For searches and help try:
*=A0=A0=A0http://www.stata.com/help.cgi?search
*=A0=A0=A0http://www.stata.com/support/statalist/faq
*=A0=A0=A0http://www.ats.ucla.edu/stat/stata/


*
*=A0=A0=A0For searches and help try:
*=A0=A0=A0http://www.stata.com/help.cgi?search
*=A0=A0=A0http://www.stata.com/support/statalist/faq
*=A0=A0=A0http://www.ats.ucla.edu/stat/stata/
=0A=0A=0A      
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/