| Running ADMB-executables |
In a DOS
window:
epil2 -est -gh 9
epil3b -est -gh 9
| |
|
SAS PROC NLMIXED and ADMB-RE
are currenlty the only software packages that allow full flexibility in formulation of
generalized linear mixed models, and automatic fitting by maximum likelihood. It is therefore of
interest to compare the performance of these packages with respect to the following criteria:
- Numerical accuracy
- Computational speed
The epilepsy data considered in Venables and Ripley Modern applied
statics with S are used. Booth et al. (2005)
fit a negative binomial loglinear mixed models to these data using NLMIXED. We consider variations over their model,
focusing on different number of random effecdts and correlation structures.
Model 1
Standard GLM-notation is used to express linear predictors.
Please refer to Booth et al. (2005) for a description
of the covariates involved.
|
|
|
# Parameters |
| Distribution |
: |
Negative binomial |
1 |
| Fixed effects part |
: |
Base*trt+Age+Visit |
6 |
| Random effects part |
: |
Base |
2 |
|
|
|
Total = 9 |
The model has two uncorrelated random effects (intercept and slope of covariate Base).
SAS and ADMB-RE give almost identical results: estimates.
Model 2
In this model the fixed effects part is reduced, while the random
part is extended to three random effects.
A full covariance structure is assumed so there are 3 variance
parameters and 3 correlation parameters (see code to the left).
|
|
|
# Parameters |
| Distribution |
: |
Negative binomial |
1 |
| Fixed effects part |
: |
Base + Age |
3 |
| Random effects part |
: |
Base + Age |
6 |
|
|
|
Total = 10 |
|