Hierarchical clustering and most other standard clustering methods such as Partitioning Around Medoids (PAM) [28] result in a binary module assignment, i.e. a node is either in or outside of a module. In some applications it may be advantageous to define a continuous, fuzzy measure of module membership for all nodes. Such measure is particularly useful to identify nodes that lie near the boundary of a module, or nodes that are intermediate between two or more modules. As explained in detail in [11], the module membership of node i in module q can be defined as
