Hi! I'm a new R user and I have a question about estimating VAR on a panel
data. What I'm trying to do is to explain stock's volume on it's
lagged
volume, it's lagged returns and lagged market return's (and vice versa).
In
addition I have generated an exogenous variable controlling for stock's
volatility. Some of you may be familiar with this experiment since it
follows Statman, Thorley & Vorkink (2004) article.
The problem is how to estimate VAR by a stock when using panel data?
Previously I have been using SAS which easily allows to estimate VAR by
variable. In this case, the SAS code is:
proc varmax data= xxx;
model VOLUME RETURN MARKETRET = VOLATILITY / p=3 ;
by STOCK;
So how to do the same thing with R?
Here is a sample of my data:
STOCK DATE RETURN MARKETRET VOLUME VOLATILITY
ALBAV 19910228 0.0000000000 1.082824e-02 1.003302e-01 3.054257e-04
ALBAV 19910327 -0.0165264410 -3.946030e-04 -2.650549e-01 3.046369e-04
ALBAV 19910430 0.0000000000 2.041973e-03 -2.682568e-01 3.038513e-04
ALBAV 19910531 0.0000000000 6.682507e-03 1.905265e-02 3.030691e-04
FUM1V 19910228 ... ...
FUM1V 19910327 ... ...
FUM1V 19910430 ... ...
NOK1V 19910228
NOK1V 19910327
NOK1V 19910430
Hope someone can help.
-Tom
--
View this message in context:
http://www.nabble.com/Vector-autoregression%2C-panel-data-tp20679144p20679144.html
Sent from the R help mailing list archive at Nabble.com.
