27.03.2013 Views

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

1010 MIXED<br />

Interpretation of Random Effect Covariance Structures<br />

This section is intended to provide some insight into the specification random effects and<br />

how their covariance structures differ from versions prior to SPSS 11.5. Throughout the<br />

examples, let A and B be factors with 3 levels, and X and Y be covariates.<br />

Example (Variance component models):<br />

Random effect covariance matrix of A:<br />

Random effect covariance matrix of B:<br />

Overall random effect covariance matrix:<br />

Prior to SPSS 11.5, this model could be specified by:<br />

/RANDOM = A B | COVTYPE(ID)<br />

or<br />

G A<br />

G B<br />

G =<br />

2<br />

σAI3 /RANDOM = A | COVTYPE(ID)<br />

/RANDOM = B | COVTYPE(ID)<br />

with or without the explicit specification of the covariance structure.<br />

As of SPSS 11.5, this model could be specified:<br />

/RANDOM = A B | COVTYPE(VC)<br />

or<br />

/RANDOM = A | COVTYPE(VC)<br />

/RANDOM = B | COVTYPE(VC)<br />

with or without the explicit specification of the covariance structure.<br />

or<br />

/RANDOM = A | COVTYPE(ID)<br />

/RANDOM = B | COVTYPE(ID)<br />

with the explicit specification of the covariance structure.<br />

=<br />

=<br />

2<br />

σBI3 G A 0<br />

0 G B 6x6

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!