Statalist


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

st: MVTOBIT, how to specify initial values for the correlation matrix


From   "Carlo Fezzi" <c.fezzi@uea.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: MVTOBIT, how to specify initial values for the correlation matrix
Date   Thu, 5 Feb 2009 19:54:48 -0000

Dear all,

I am using the Stata module MVTOBIT to estimate multivariate Tobit with 9
equations. As suggested in the help file, I am trying to reduce the
computing time giving initial values for the correlation and standard
deviation matrix using the atrho0(matrix) option.

Apologies if this might look dull, but from the help file I cannot figure
out how this matrix has to be specified. The help states:

atrho0(matrix_name) allows users to specify starting values for the standard
deviations and correlations that are different from the default values
(zeroes and ones, respectively).  The matrix matrix_name contains values of
the incidental parameters, /lnsigmai and /atrhoij, for the M equations.
Matrix matrix_name must have properly named column names. E.g., if a
starting value in /atrho12 is being set, one would first use the command
matrix matrix_name = (value), followed by matrix colnames matrix_name =
atrho12:_cons. Between 1 and M(M-1)/2 /atrhoij, and between 1 and M
/lnsigmai starting values may be specified, where i = 1,...,M-1, and j > i.
One likely source for a non-default starting value for atrhoji is the
/athrho parameter estimate from a bivariate model corresponding to equations
i and j of the full mvtobit model.

I tried to follow the instructions to understand what was going on simply
typing:

matrix matt = (0.21) 
matrix colnames matt = atrho12:_cons

But MVTOBIT stops with the message:

?initial values not feasible?

Whereas if I do not specify the option ?atrho0(matt)? the code works fine.
If anybody could provide an example of how this option has to be properly
used I would be really grateful.

All the best,

Carlo


**************************************************
Carlo Fezzi
Senior Research Associate
Centre for Social Research on the Global Environment (CSERGE)
Department of Environmental Sciences
University of East Anglia
Norwich (UK) NR2 7TJ 
Telephone: +44(0)1603 591385
Fax: +44(0)1603 593739
*************************************************



*
*   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   |   What's new   |   Site index