Thread: Applying multiple regression results to new data SPSS

1. Applying multiple regression results to new data SPSS

My study involves testing infants at multiple time points using a number of behavioural tests.

I used a multiple regression to establish which behavioural variables could predict severity of outcome score at the end of the testing.

So, I tested infants at 14 months and used a regression model to identify whether scores from any of the behavioural variables could predict better or worse scores at 24 months.

my model works fine and 4 IV's significantly predicted severity of outcome. But now I want to use this regression model to see whether it can predict 24m outcomes from a new dataset with new infants - BUT they have been tested on the same IV's and DV's.

Does anyone know how I might go about doing this in SPSS?

Thank you

2. Re: Applying multiple regression results to new data SPSS

Followed you all of the way up until your last sentences. I got confused because it sounded like you just wanted to repeat the whole process - which I would imagine you know how to do.

3. Re: Applying multiple regression results to new data SPSS

Hi,
i do not know Spss but most statistics programs have "predict" function for such cases, that can be used once the model has been specified. For a simple multiple regression you could even use Excel - just implement the model formula in Excel and let it calculate the predictions for the new data.

I hope this helps

4. Re: Applying multiple regression results to new data SPSS

There are a couple of ways to do it at least. One way I know how to do it is to combine your two samples with all your IVs and keep the DV as missing data for you new sample. The data from sample 1 used for estimating the model will have values for the DV

/SAVE pred(prediction1) or select the save predicted option in the dialogs

This will save the predicted values in a variable called prediction 1. SPSS will estimate the model based on the sample 1 cases which have values for the DV and will predict values for all cases for sample 1 and sample 2.

A second manual way is just to use the TRANSFORM-COMPUTE VARIABLE function and manually create the formula with your coefficients.

There is another way where you can save the derived regression model to an xml file and use an APPLY_MODEL function but I haven't used that.

To use a model XML you either save the model parameters to a file using the SAVE dialog or use the following syntax clause in your regression

/OUTFILE=model('mymodelparametrs.xml')

This will save the estimated model to an xml file.

Then open your new sample and to use the parameters with your new sample.

* Open the saved model.
MODEL HANDLE NAME = mymodel file='mymodelparameters.xml'.

* Compute predictions.
COMPUTE myprediction= ApplyModel(mymodel,'predict').

 Tweet

Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts