Variance of the predictions of the etas.

From: "HUTMACHER, MATTHEW" <MATTHEW.HUTMACHER@chi.monsanto.com> Subject: Variance of the predictions of the etas. Date: Wed, 22 Sep 1999 14:02:14 -0500 Hello all, I was wondering if anyone knew an easy way to get NONMEM to output an estimate of the variance of the empirical Bayes predictions (the etas). To be more precise, let "cl_eta_i" be the true value of the variance component on clearance for individual i, let "p_cl_eta_i" be the empirical Bayes prediction for cl_eta_i. What I would like to calculate is VAR(p_cl_eta_i - cl_eta_i). Actually, in a more general sense, let "eta_i" be the vector of the true values of the variance components for individual i, and "p_eta_i" the prediction. Is there an easy way to get the matrix VAR(p_eta_i - eta_i)? Thank you. Matt