Hi everyone,
I need help with a Stata command. In the "regress" command, there
is an option "cluster." Apparently, it is used when the data is
such that some of the observations may be correlated. For example,
if I estimate a specification using time series-cross section
pooled data of n banks and t years. Since the portfolios and many
of the financial ratios of each of the banks, used in the
specification, may be correlated across the t years, it seems to
me that I should use the "cluster" option. Am I mistaken? What
exactly is the econometrics of the "cluster" option? Thanks!
Regards,
Sumon
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
