Effects of Ignoring Correlations
in Longitudinal Response or Covariate Processes
Naisyin Wang
The analysis of hierarchical biomedical data sometimes requires more modeling flexibility than that can be provided
by standard parametric approaches. It is commonly believed that the effect of ignoring covariance structure is mainly on the lost of efficiency. In this talk, I will use some numerical outcomes and examples to illustrate some potential concerns when one ignores the correlations in longitudinal measurements. The less known fact is the serious level of biases that could be induced by ignoring existing correlations. Some solutions would be provided.