Dear Statalisters,
I am trying to implement a Variance Decomposition analysis and to follow
previous literature in accounting research
I am asked by reviewers to present for each variance component two numbers:
- the weighted least square point estimate of the parameter (where
observations are weighted such that each cross-section receives an equal
weight) and
- a robust Jacknife standard error.
I use Vecar to estimate the VAR model and then proceed to compute the
variance decomposition with a matrix calculation using the coefficients and
the variance-covariance matrices from the Vecar command.
In this way, however, I am not able to compute the robust Jacknife standard
error.
Any advice would be greatly appreciated.
Thanks in advance,
Giorgio
*
* 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/
