A Mixed-Effects Model for Analyzing Cluster-Level Non-Ignorable
Missing Data
Description
Contains functions for estimating a mixed-effects model for
clustered data (or batch-processed data) with cluster-level (or batch-
level) missing values in the outcome, i.e., the outcomes of some
clusters are either all observed or missing altogether. The model is
developed for analyzing incomplete data from labeling-based quantitative
proteomics experiments but is not limited to this type of data.
We used an expectation conditional maximization (ECM) algorithm for model
estimation. The cluster-level missingness may depend on the average
value of the outcome in the cluster (missing not at random).