Embodiments of the present invention are directed to identifying a source of bias in a sample set and using statistical techniques to overcome the bias, thereby producing extrapolated data that accurately represents a population including the sample set. The method according to one embodiment comprises identifying a plurality of attributes corresponding to an entity, generating a plurality of clusters from the plurality of attributes, the plurality of clusters including varying numbers of the plurality of attributes, and performing measurements on each of the plurality of clusters to generate measurement data values for each of the plurality of clusters. A cluster with a greatest measurement data value is selected.