Statalist


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

st: Re: RE: generating correlated binary data


From   "Martin Weiss" <[email protected]>
To   <[email protected]>
Subject   st: Re: RE: generating correlated binary data
Date   Sun, 14 Jun 2009 11:58:00 +0200

<>

Joseph,


the ovbd_illustrator.do file sets the -seed- in a manner that makes it incompatible with Stata 10. At least I can only make the line

set seed `=date("2007-02-27", "ymd")'

run by setting -vers 9-. For 10, I have to switch to

set seed `=date("2007-02-27", "YMD")'

HTH
Martin
_______________________
----- Original Message ----- From: "Joseph Coveney" <[email protected]>
To: <[email protected]>
Sent: Sunday, June 14, 2009 6:22 AM
Subject: st: RE: generating correlated binary data


David Airey wrote:

What is the easiest way of generating correlated binary data (greater
than 2 observations per cluster) in Stata?

I am trying to download this paper:

Al-Osh and Lee (2001) A simple approach for generating correlated
binary variates. J. Statist. Comput. Simul. Vol. 70, pp. 231-255.

--------------------------------------------------------------------------------

You can download -ovbd- from SSC to generate correlated binary data with two or more observations per cluster. You'll also need to have another user-written
command installed, -ridder-, which is called by -ovbd-.

The syntax for -ovbd- is directly analogous to that of -drawnorm-, except for the -sd()- option, of course. For the same reason, there are constraints on what you can specify for a combination of mean vector and correlation matrix.

Joseph Coveney



*
*   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/


*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index