Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: A Question Regarding -xtunitroot-

From   Scott Merryman <>
Subject   Re: st: A Question Regarding -xtunitroot-
Date   Sat, 8 Sep 2012 19:55:21 -0500

1.  There are no pvalues when the noconstant option is used in
-dfuller-, therefore is nothing for -xtunitroot fisher- sum.

2.  There is no fixed effect constant (such produced by -xtreg, fe-)
because each panel is analyzed separately.


On Sat, Sep 8, 2012 at 12:01 AM, Yuval Arbel <> wrote:
> Dear Statalisters,
> I used the command -xtunitroot- to test for unit roots in all panels
> and ran Fisher-Type tests.
> The problem is that I would like to suppress the constant generic
> fixed effect terms (by -noconstant-). This possibility is not
> available for Fisher-Type tests.
> I tried other tests, which have the -noconstant- option, but the
> problem is that my panel is unbalanced, and these tests cannot be
> performed on an unbalanced panel.
> The question is can I do something about it? can I at least run a test
> to see whether these generic fixed effect terms are equal to zero?
> --
> Dr. Yuval Arbel
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index