1
$\begingroup$

When running the Automatic Linear Modeling function of SPSS version 20, it will return an accuracy value.

The higher the accuracy, the more predictive the model (I assume). However, what does this accuracy really indiciate?

Is it the R2? Adjusted R2? Something else?

$\endgroup$
1
$\begingroup$

I believe that it is the adjusted R2, but you can check this by using a regular REGRESSION command that matches your linear specification to see if the statistics match.

HTH

$\endgroup$
1
  • $\begingroup$ That's what I wanted to do, but the problem is that the automatic linear modeling output never actually gives you the model itself, with all precise coefficients etc. $\endgroup$ – Tom Jan 12 '12 at 16:50
-1
$\begingroup$

Before you run the analysis you have to assign an output file in the third tab under "Predicted Value." Then you have to go to utilities and select scoring wizard, choose the model you just saved and it will automatically assign the predicted values to the rest of the data set.

$\endgroup$
1
  • 1
    $\begingroup$ What has this to do with accuracy as asked by th OP? $\endgroup$ – Henrik May 18 '12 at 22:05

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.