IBM Support

Mallow's CP, Akaike (AIC), Amemiya (PC), or Schwarz Bayesian Criterion (SBC)

Troubleshooting


Problem

I would like to use a selection criterion such as Mallow's CP, the Akaike Information Criterion (AIC), the Amemiya Prediction Criterion (PC), or the Schwarz Bayesian Criterion (SBC) in order to help avoid regression models with an excessive number of parameters. Is there any way I can obtain these selection criteria in SPSS Regression?

Resolving The Problem

The selection criteria can be requested through SPSS command syntax, by adding SELECTION to the /STATISTICS subcommand.

Mallow's CP, Akaike Information Criterion (AIC), the Amemiya Prediction Criterion, and the Schwartz Bayesian Criterion will then appear in the Model Summary table.

These criteria currently cannot be requested through the Regression dialog box. However you may set up the model as you normally would using the Analyze->Regression->Linear, but do not click the OK button. Instead click Paste, add the word SELECTION to the /STATISTICS subcommand, and execute the syntax using the Run menu.

An enhancement request has been filed with SPSS Development, asking that a checkbox be added to the Statistics dialog box for Linear Regression so that these statistics may be requested via the dialog boxes. We apologize for any resulting inconvenience.

[{"Product":{"code":"SSLVMB","label":"IBM SPSS Statistics"},"Business Unit":{"code":"BU059","label":"IBM Software w\/o TPS"},"Component":"Not Applicable","Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"Not Applicable","Edition":"","Line of Business":{"code":"LOB10","label":"Data and AI"}}]

Historical Number

21685

Document Information

Modified date:
16 April 2020

UID

swg21476978