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, statalist.org is already up and running.


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

Re: st: Testing for serial correlation in small panel samples


From   christina sakali <christina.sakali@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Testing for serial correlation in small panel samples
Date   Thu, 8 Sep 2011 04:16:44 +0300

Thank you very much for the information and references, this is very helpful!

Can you also please clarify this bit of information:
Is the BFN Durbin Watson stat. an appropriate test for serial
correlation even if the error distribution is NOT normal? (since the
original DW stat. cannot be used in the case of non-normality).

On 7 September 2011 21:10, Scott Merryman <scott.merryman@gmail.com> wrote:
> It is based on -xtreg,fe-   The BFN Durbin Watson is also easy to calculate.
>
> Compare:
>
> webuse grunfeld,clear
> qui xtregar inv mva, fe lbi
> disp "modified Bhargava et al. Durbin-Watson = " e(d1)
>
> qui xtreg inve mval, fe
> predict double e,e
> gen double bfn = sum((e- l.e)^2)/sum(e^2)
> cl bfn in l, noobs
>
>
> The original BFN paper supplies upper and lower bounds for Durbin
> Watson statistic.   For a large number of cross sections, if it less
> than 2 then it would indicate positive serial correlation.
>
> See:
>
> Bhargava, A., Franzini, and W. Narendranathan. 1982. "Serial
> correlation and fixed effects model." Review of
>    Economic Studies 49, p. 533 - 549.
>
> and
>
> http://books.google.com/books?id=uEFm6pAJZhoC&lpg=PP1&pg=PA374#v=onepage&q&f=false
>
>
> Scott
>
> On Wed, Sep 7, 2011 at 12:09 PM, christina sakali
> <christina.sakali@googlemail.com> wrote:
>> Dear Scott,
>>
>> thanks a lot for the suggestion.
>>
>> I have a question though: Does the Bhargava et al's DW stat., reported
>> by the -lbi- option, refer to the original xtreg regression or the
>> xtregar one, which is corrected for first-order serial correlation?
>>
>> I guess what I need to know is: can I use the Bhargava stat. from the
>> -lbi- option  as an indication of serial correlation in my original
>> xtreg regression or is this irrelevant?
>>
>
> *
> *   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/
>

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index