compute_optimal_clustering function

Compute the optimal clustering from an MCMC sample

Summarizes the posterior on all possible clusterings by an optimal clustering where optimality is defined as minimizing the posterior expectation of a specific loss function, the Variation of Information or Binder's loss function. Computation can be lengthy for large datasets, because of the large size of the space of all clusterings.

compute_optimal_clustering(fit, loss_type = "VI")

Arguments

• fit: The fitted object, obtained from one of the MixNRMIx functions
• loss_type: Defines the loss function to be used in the expected posterior loss minimization. Can be one of "VI" (Variation of Information), "B" (Binder's loss), "NVI" (Normalized Variation of Information) or "NID" (Normalized Information Distance). Defaults to "VI".

Returns

A vector of integers with the same size as the data, indicating the allocation of each data point.