✍ Scribed by Alan Hartford; Marie Davidian
No coin nor oath required. For personal study only.
The nonlinear mixed e ects model provides a framework for inference in a number of applications, most notably pharmacokinetics and pharmacodynamics, but also in HIV and other disease dynamics and in a host of other longitudinal-data settings. In these models, to characterize population variation, individual-speciÿc parameters are modeled as functions of ÿxed e ects and mean-zero random e ects. A standard assumption is that of normality of the random e ects, but this assumption may not always be realistic, and, because the random e ects are not observed, it may be di cult to verify. An additional issue is specifying the form of the function relating individual-speciÿc parameters to ÿxed and random e ects. Again, because this relationship is not observed explicitly, it may be di cult to specify. Popular methods for ÿtting these models are predicated on the normality assumption, and past studies evaluating their performance have assumed that normality and the form of the model are correct speciÿcations. We investigate the consequences for population inferences using these methods when the normality assumption is inappropriate and=or the model is misspeciÿed.
📜 SIMILAR VOLUMES