Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Clustering, Fixed Effects, or else?
From
Leigh Lee <[email protected]>
To
[email protected]
Subject
st: Clustering, Fixed Effects, or else?
Date
Fri, 21 May 2010 01:16:35 -0400
Hi,
I intend to estimate the following model: Y(i,t)=X(i,t)+Z(t), where i
denotes units and t denotes months. Y is updated monthly, and it
exhibits auto-correlation. Some variables in the X matrix are updated
monthly, but some are updated quarterly. Z is the variable I am
interested at, but it is time-variant only (by month). What is the
best means to get reliable inference (standard errors) of the effect Z
has on Y.
To test my next hypothesis, I further want to estimate the following:
Y(j,i,t)=X(i,t)+Z(t), where i denotes units and t denotes months as
above and j denotes subjects in each unit i. Once again, I am not
sure what is the best estimation method.
Thanks in advance for your help!!
Best,
Leigh
*
* 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/