Defining the data source

The first step in the PROXMAP analysis involves defining the data to be used. In the Proximity Mapping dialog box, go to the Data tab to define the data (see Figure 1).

Eight numerical variables are selected as input variables for computing proximities based on multivariate data: popul, income, life, school, illit, fail, homic, and freeze. The selected source is labeled States data and automatically named $SRC001 in the source list.

The variable STATE was assigned as the object label, helping ensure that each point (US state) is clearly identified in the output. The categorical variable region does not contribute to the proximity computation. But it is used for the interpretation of the solution.

In the main dialog, select the following four variables for analysis: These variables are chosen due to their relevance in evaluating customer financial stability and loan repayment potential.

Figure 1. Choosing variables
The Data Type is specified as Multivariate data and Standardized Euclidean.
  • Multivariate data indicates that proximities are computed internally from the selected variables.
  • Standardized Euclidean helps ensure that all quantitative variables are standardized to equalize their contribution.