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: xtscc Vs xtpcse
From
Eshita Gupta <[email protected]>
To
[email protected]
Subject
st: xtscc Vs xtpcse
Date
Thu, 18 Jul 2013 08:46:17 +0530
Dear statalist,
I have TSCS (Time series cross-section data) on electricity demand
and daily weather variables such as temperatures and rainfall for 30
states and 5 years. I have created a panel dataset at the daily level
and there are some variables in the model that change annually such as
income and prices. So for each state I have data for 5 years or 1796
days.
Can anyone guide me as when we predict after
xtpcse, what exactly we get? how can we interpret the linear
prediction after xtpcse? Can I compare prediction errors from pooled
OLS and prediction errors from xtpcse. How should I select between
POLS and xtpcse?
whether I should use OLS estimates and just correct for the standard
errors or I use the xtpcse providing new estimates after correcting
for autocorrelation.
POLS with correct standard error: xtscc y x
xtpcse accounting for autocorelation: xtpcse y x, correlation(psar1)
Thanks
Eshita
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/