Usage Note 24285: How can I test for equality of parameters in two or more models that contain different predictors?
The TEST or MTEST statement in PROC REG does not support hypothesis testing across multiple MODEL statements. However, you can do this testing by using the STEST statement in SAS/ETS PROC SYSLIN. For example, the following statements test the hypothesis that the X1 and X2 parameters are equal in these two models that are fit by using ordinary least squares:
proc syslin ols;
model y1=x1;
model y2=x2;
stest y1.x1 = y2.x2;
run;
This method can be extended to any number of models and can be used with other estimation methods that are supported by PROC SYSLIN (except FIML).
If you want to test the equality of parameters in models that are fit to independent groups, where the models use the same predictors, this can be done using an analysis of covariance (ANCOVA) approach as discussed
here.
Operating System and Release Information
| SAS System | SAS/STAT | All | n/a | |
| SAS System | SAS/ETS | All | n/a | |
*
For software releases that are not yet generally available, the Fixed
Release is the software release in which the problem is planned to be
fixed.
| Type: | Usage Note |
| Priority: | low |
| Topic: | SAS Reference ==> Procedures ==> REG
Analytics ==> Multivariate Analysis
SAS Reference ==> Procedures ==> SYSLIN
Analytics ==> Econometrics
Analytics ==> Structural Equations
Analytics ==> Regression
|
| Date Modified: | 2005-07-01 07:35:28 |
| Date Created: | 2005-05-31 16:29:57 |
