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 at the end of May, and its replacement, statalist.org is already up and running.


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

st: time-trend in correlation equation


From   Bülent Köksal <bkoksal@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: time-trend in correlation equation
Date   Mon, 27 Feb 2012 14:15:13 +0200

Dear Stata Users,

I am calculating 90-days rolling-window correlations between
conditional volatilities of daily returns for two stocks as follows:


webuse stocks, clear

forvalues i=90(1)180 {
local j=`i'-89
mgarch ccc (toyota nissan= , noconstant) in `j'/`i', arch(1) garch(1) nolog
}


Two questions:

1. How can I accumulate correlations and standart errors in a file?

2. To control for time-effects in variances, we can include a
time-trend to the model:

.mgarch ccc (toyota nissan= L.toyota L.nissan, noconstant), arch(1)
garch(1) het(t)

My second question is, let's say that the correlations calculated
above increases. How can we test whether this increase is
statistically significant? Some papers included a time-trend in the
correlation equation. Is this possible in Stata, or is programming
necessary to achieve this task? Thanks.

bülent

*
*   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