Two Step Cluster

From Q
Jump to navigation Jump to search

Two Step Cluster is IBM's brand name for a variant of Mixed-Mode Cluster Analysis.

The key differences between the two methods are that:[note 1]

  • Q's algorithm can also address MaxDiff, ranking, conjoint and discrete choice data (whereas these first need to be treated as numeric data in the IBM algorithm).
  • Q assumes spherical clusters by default. This can changed by setting Distribution to Multivariate - Diagonal in the Advanced option.

Notes

Template:Reflist

Further reading: Latent Class Analysis Software
Cite error: <ref> tags exist for a group named 'note', but no corresponding <references group='note'/> tag was found