Cholesky decomposition with many vari... PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Sanja Franic posted on Sunday, April 04, 2010 - 12:46 pm
Hi, I am trying to estimate a 24x24 covariance matrix subject to the requirement that it be positive definite, so I am estimating its Cholesky decomposition. However given that I have 24 variables it would be too cumbersome to specify a script like e.g. this one:

Data: file is 'data1.dat';
Variable: names are x1-x3;
usev are x1-x3;
Analysis: iter=5000;

Model:
x1(v1);
x2(v2);
x3(v3);
x1 with x2 (c12);
x2 with x3 (c23);
x1 with x3 (c13);

model constraint:

new(p11 p12 p13 p22 p23 p33);
v1=p11^2;
v2=p12^2+p22^2;
v3=p13^2+p23^2+p33^2;
c12=p11*p12;
c13=p11*p13;
c23=p13^2+p23^2+p33^2;

Is there a simple way to estimate a Cholesky decomposition for a large number of variables?

Thanks,
Sanja
 Linda K. Muthen posted on Monday, April 05, 2010 - 8:02 am
Mplus does not have an option for Cholesky decomposition.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: