Addresses the issue of different measurement scales for continuous and ordinal columns. Except when the Data is stacked option is selected, the values in each column are standardized by subtracting the column mean and dividing by the column standard deviation. Deselect the Standardize Data check box if you do not want the cluster distances computed on standardized values.

Note: If both Standardize Data and Standardize Robustly are selected, each column is standardized by subtracting its robust column mean and dividing by its robust standard deviation. This option is useful when columns represent different measurement scales or when observations tend to be outliers in only specific dimensions.

Note: If Standardize Data is unchecked and Standardize Robustly is selected, the robust mean and robust standard deviation for the values in all columns combined are used to standardize each column. This option can be useful when columns all represent the same measurement scale and when observations tend to be outliers in all dimensions.

Multivariate SVD imputation avoids constructing a covariance matrix by using the singular value decomposition. For more details, see Explore Missing Values Utility in the Predictive and Specialized Modeling book.

(Available only if Data is stacked is selected as the data structure.) Select the Add Spatial Measures option when your data are stacked and contain two attribute columns that correspond to spatial coordinates (horizontal and vertical coordinates, for example). This option opens a window in which you can select which spatial components to add measures for circle, pie, and streak spatial measures to aid in clustering defect patterns. This is a specialty method and is applicable in only very specific settings. See Spatial Measures and Example of Wafer Defect Classification Using Spatial Measures.