Advertisement

Building on the methodology developed in this text, the current chapter presents five case studies. In Section 24.1, we study the extension of univariate longitudinal data technology to the multivariate setting, where several measurements (i.e., systolic and diastolic blood pressure) are obtained at each measurement occasion. Section 24.2 is devoted to a developmental toxicology experiments where, due to litter effects, fetuses are clustered within dams. The flexibility of the linear mixed model to combine cluster effects with individual-specific covariates is illustrated. Even though time is not a factor in these data, we are able to establish a close connection with longitudinal modeling. In Section 24.3, we describe how bivariate outcomes from multicenter trials can be used to study the validity of one outcome as a surrogate endpoint for the other. A sensitivity analysis on incomplete longitudinal data on milk protein content is conducted in Section 24.4. The chapter is concluded with the analysis of hepatitis B vaccination data. It is shown how rather irregular sequences can be handled within the linear mixed-models context.

Keywords

Linear Mixed Model Longitudinal Data Milk Protein Surrogate Endpoint Cluster Effect 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Verlag New York, LLC 2009

Personalised recommendations