MODEL subcommand (SIMPLAN command)

The MODEL subcommand specifies the file containing the model that is to be simulated. You can specify an IBM® SPSS® model file (an XML file or a compressed file archive (.zip file) that contains model PMML created from IBM SPSS Statistics or IBM SPSS Modeler) or a file created from a SIMPREP BEGIN-SIMPREP END block. SIMPREP BEGIN-SIMPREP END blocks create a model, for use with SIMPLAN, based on a set of custom equations that you define.

FILE = 'filespec'. Specifies the model file. File specifications should be enclosed in quotation marks and fully qualified paths are recommended to avoid ambiguity. The file is assumed to be a model file unless it has an extension of .splan, in which case it is treated as a simulation plan file from which the model file will be extracted.

Note: The optional combination of an asterisk (*) and a backslash (\) preceding the model file name specifies that the file is a temporary file. This only applies in the case that SIMPLAN CREATE follows a SIMPREP BEGIN-SIMPREP END block. See the topic OUTFILE subcommand (SIMPREP BEGIN-SIMPREP END command) for more information.

CUSTOM = YES | NO. Specifies whether the model consists of a set of custom equations. Models for sets of custom equations are created using a SIMPREP BEGIN-SIMPREP END block. The default is NO, which specifies that the model was not created by a SIMPREP BEGIN-SIMPREP END block.

PMML models supported by Simulation

  • Linear Regression
  • Automatic Linear Model
  • Generalized Linear Model
  • Generalized Linear Mixed Model
  • General Linear Model
  • Binary Logistic Regression
  • Multinomial Logistic Regression
  • Ordinal Multnomial Regression
  • Cox Regression
  • Tree
  • Boosted Tree (C5)
  • Discriminant
  • Two-step Cluster
  • K-Means Cluster
  • Neural Net
  • Ruleset (Decision List)
Note:
  • PMML models that have multiple target fields (variables) or splits are not supported for use in Simulation.
  • Values of string inputs to binary logistic regression models are limited to 8 bytes in the model. If you are fitting such string inputs to the active dataset, make sure that the values in the data do not exceed 8 bytes in length. Data values that exceed 8 bytes are excluded from the associated categorical distribution for the input, and are displayed as unmatched in the Unmatched Categories output table.