Select the Robust Normal Mixtures method from the Method menu of the Iterative Clustering Control Panel (Control Panel for Normal Mixtures Method).
Several of the options on the panel are described in Iterative Clustering Control Panel. The remaining options are described as follows:
A number between 0 and 1. Robust Normal Mixtures protects against outliers by down-weighting them. Huber Coverage loosely reflects the proportion of the observations that are not considered outliers, and not down-weighted. Values closer to 1 result in a larger proportion of the data not being down-weighted. In other words, values closer to 1 protect only against the most extreme outliers. Values closer to 0 result in a larger proportion of the data being down-weighted, and might falsely consider less extreme data points to be outliers. For details, see Additional Details for Robust Normal Mixtures.