Database Reference
In-Depth Information
rotation), and equally represent all the underlying, input data dimensions. These
characteristics make themperfect candidates for inclusion in subsequent clustering
algorithms for segmentation.
RECOMMENDED PCA OPTIONS
Figures 3.3 and 3.4 and Table 3.8 present the recommended options for fine
tuning the PCA model development process in IBM SPSS Modeler (formerly
Clementine) and in any other data mining software which offers the specific
technique. Although IBM SPSS Modeler integrates smart defaults appropriate for
Figure 3.3 IBM SPSS Modeler recommended PCA/Factor Model options.
Search WWH ::




Custom Search