Clustering with missing data: which equivalent for Rubin’s rules?

Multiple imputation (MI) is a popular method for dealing with missing values. However, the suitable way applying clustering after MI remains unclear: how to pool partitions? How assess instability when data are incomplete? By answering both questions, this paper proposed complete view of using MI. The problem partitions pooling here addressed consensus while, based on bootstrap theory, we explain related observed and data. new rules assessment theoretically argued extensively studied by simulation. Partitions improves accuracy, while measuring enlarges analysis possibilities: it allows dependence model, as well convenient choosing number clusters incomplete, illustrated real set.