Hello all,
I have a frustrating problem I know someone can quickly fix.
I am trying to assign colnames to a matrix and I have included a snippet
of code below.
It should be the case (IMHO) that theta_V and theta will have same
colnames, but they don't.
With the code below, theta_V has equation names specified (in this case a
generic c1:) which are NOT in theta matrix.
If I change line 4 in the code below to matrix `theta_V'=J(4,4,1) for
example, the problem disappears and all colnames are as expected.
I have supposed the problem (feature) is that by taking the product of
(tmp'tmp) Stata introduces equation names.
How do I avoid this problem?
***********Code Snippet***************
local names: colnames `theta'
matrix `theta_h'=J(1,`n',1/`n')*`theta'
matrix `tmp'=`theta'-J(`n',1,1)#`theta_h'
matrix `theta_V'=`tmp''*`tmp'/(`n'*(`n'-1))
matrix rownames `theta_V'=`names'
matrix colnames `theta_V'=`names'
*************************************
Thanks in advance,
Ed
Edward F. Blackburne III, PhD
Associate Professor
Economics and International Business
Sam Houston State University
blackburne@shsu.edu
936-294-3934
*
* 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/