Desktop version

Home arrow Economics arrow Applied Surrogate Endpoint Evaluation Methods with SAS and R

Source

Convergence Problems in Fitting Linear Mixed- Effects Models

In a surrogate evaluation context, the (S, T) endpoints (level 1) are nested within patients (level 2), and the patients are nested within clinical trials

(or other relevant clustering units; level 3). Given the complex hierarchical structure of the data, it is hardly surprising that convergence problems are frequently encountered in a surrogate evaluation context. To gain more insight into the factors that affect the convergence of hierarchical models, simulations can be useful.

A Simulation Study

Simulation scenarios

Consider the following mixed-effects model that is typically fitted to evaluate surrogacy in the setting when both S and T are normally distributed endpoints (see also Chapter 4):

where ps, pT are the fixed intercepts for S and T, mSi, mTi are the corresponding random intercepts, a, в are the fixed treatment effects for S and T, and ai, h are the corresponding random treatment effects. Further, (msi, mTi, ai, 6j) ~ N (0, D), with D an unstructured variance-covariance matrix of the random effects, and (eSij, ?Tij) ~ N (0, E) with E an unstructured variance-covariance matrix of the residuals.

Using Model (15.1), data were simulated. In all simulations, ps = 450, pT = 500, a = 300, в = 500, and

yielding R2ndiv = corr (eSij, ?Tij )2 =0.5. Three conditions were varied in the simulations. First, the number of clusters N = {5, 10, 20, 50}. Second, the between-cluster variability (D), which is either large (7 = 1) or small (7 = 0.1) relative to the residual variability (E):

yielding R‘2liai = corr(ai, hi)2 = 0.5. Third, the level of imbalance in the cluster sizes n (the rationale to consider this factor is described in more detail in the next paragraph). In the balanced scenario, all cluster sizes were equal, i.e., n = n = 20. In the two unbalanced scenarios, n was determined based on a draw from a normal distribution and rounded to the nearest integer (i.e., Ui = round (U*)). In the low-imbalance scenario, n ~ N (20, 2.Б2). In the high-imbalance scenario, n ~ N (20, 52). In the balanced scenario, treatment (Z) is also balanced within a cluster. In the unbalanced scenarios, treatment allocation is determined based on a binomial distribution with success probability 0.50.

 
Source
Found a mistake? Please highlight the word and press Shift + Enter  
< Prev   CONTENTS   Next >

Related topics