Troubleshooting
Problem
Can SPSS do reduced major axis regression?
Resolving The Problem
There is not a built in procedure for reduced major axis regression in SPSS, but this model can easily be fitted using the CNLR procedure. If Y is the dependent variable and X is the predictor or independent variable, the command syntax would be:
MODEL PROGRAM A=1 B=1.
COMPUTE PRED=A+B*X.
COMPUTE LOSS=(Y-PRED)**2/ABS(B).
CNLR Y /LOSS=LOSS.
Bootstrapped estimates of standard errors are also available.
All of these specifications are available in the dialog boxes. However, working in the dialogs, to specify the loss function, you would have access to only variables named PRED_ and RESID_, so the loss function specification could be written as (Y-PRED_)**2/ ABS(B) or RESID_**2/ABS(B).
Related Information
Historical Number
12739
Was this topic helpful?
Document Information
Modified date:
16 April 2020
UID
swg21476031