Covariance Parameters

Figure 1. Estimates of covariance parameters for unstructured covariance model
Estimates of covariance parameters for unstructured covariance model

The covariance parameter estimates table directly reports the values for the unstructured matrix.

  • UN(1,1) is the variance for the intercept. The large value of the estimate suggests there is a fair amount of patient-to-patient variation in the starting weight.
  • UN(2,2) is the variance for the time coefficient. Since the significance value is greater than 0.10, you cannot conclude that there is appreciable patient-to-patient variability in this coefficient.
  • UN(2,1) is the covariance between the intercept and the time coefficient. Since the significance value is greater than 0.10, you cannot conclude that there is any correlation between these terms.
Figure 2. Random effect covariance (G) matrix for unstructured covariance model
Random effect covariance (G) matrix for unstructured covariance model

The G matrix is shown in matrix format for easy reference.

Next