Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: How to report two normally distributed variables with a correlation structure?


From   tiago.pereira@incor.usp.br
To   statalist@hsphsun2.harvard.edu
Subject   st: How to report two normally distributed variables with a correlation structure?
Date   Tue, 22 Jul 2008 14:10:06 -0300 (BRT)

Dear Statalisters,

I have used Stata to generate bivariate normally distruted variables.
Instead of using a covariance matrix, I imput a correlation matrix. For
example,

set obs 1000
matrix COR = (1,0.95\0.95,1)
matrix SD = (20,10)
matrix MEANS = (120, 100)
drawnorm x y, means(MEANS) sds(SD) corr(COR)

In this respect, I would like to know how does one report this procedure
in terms of statistical notation. I mean, what would be the most correct
way to report it, since I donīt work with a covariance matrix, which would
facilitate a lot statistical notation for non-statisticians like me. I
have used:

(Y1,Y2) ~BVN(mu1,mu1,sig1^,sig2^2,rho), as a single vector. Is that correct?

All the best,

Tiago





*
*   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