Böcker av Michael J. (University of Florida Daniels

Bayesian nonparametric (BNP) methods can be used to flexibly model joint or conditional distributions, as well as functional relationships. These methods, along with causal and/or missingness assumptions, can be used with the g-formula to infer causal effects.

Offers a unified Bayesian approach to handle missing data in longitudinal studies. This book contains examples and case studies on aging and HIV. It describes assumptions that include MAR and ignorability, demonstrate the importance of covariance modeling with incomplete data, and cover mixture and selection models for nonignorable missingness.