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: Can GLLAMM Allow for Autocorrelation?


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Can GLLAMM Allow for Autocorrelation?
Date   Tue, 12 Oct 2010 09:51:12 -0400

Sorry, Stas--
I already told her to ask you.

On Mon, Oct 11, 2010 at 11:54 PM, Stas Kolenikov <skolenik@gmail.com> wrote:
> Looks more like a state-space model, see -sspace- in Stata 11. Talk to
> Austin :))
>
> On Mon, Oct 11, 2010 at 5:34 PM, Zhang, Sisi <SZhang@urban.org> wrote:
>> Dear Statalist,
>>
>> I use gllamm to estimate the following model:
>>
>> y(it)=Xb+a(t)mu(i)+v(it)           eq(1)
>> v(it)=rho*v(i,t-1)+e(it)           eq(2)
>>
>> The model works well when I estimate eq(1), assuming v(it) is iid. However,
>> I would like to allow autocorrelations in v(it), such as AR(1) process in
>> eq(2). Could gllamm do that? A further question is, could gllamm estimate a
>> model with both autocorrelation and loading factors on v(it) as the
>> following model? Thanks a lot!!
>>
>> y(it)=Xb+a(t)mu(i)+b(t)v(it)       eq(1)
>> v(it)=rho*v(i,t-1)+e(it)           eq(2)
>>
>>
>> Best,
>>
>> Sisi

*
*   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