SPSS Neural Networks Tutorial

NN for time series: values of each lag Yt-1, Yt-2… become a new variable in the NN.
Factors: nomial / categorical vars.Covariates: numeric vars.

SPSS: Enter > Open Data File > choose your file.
image33

Choose from Analyze tab > Neural Networks > Multilayer perceptron.

image36

In the output tab:
image31

Classification
Sample Observed Predicted
No Yes Percent Correct
Training No 324 30 91.5%
Yes 62 57 47.9%
Overall Percent 81.6% 18.4% 80.5%
Testing No 152 11 93.3%
Yes 33 31 48.4%
Overall Percent 81.5% 18.5% 80.6%
Dependent Variable: Previously defaulted

SPSS: Neural Networks: Multilayer Perceptron – Ratdial Basis Function

NN in SPSS: if
Classification: how good our model is: Matching between predicted and actual Yes-Yes and No-No:

image34

Importance of factors and covariates:

image32

image35

SPSS Independent Variable Importance

 

Receiving Operating Curve: The farther it is from the diagnol the better the model:

image37

NN_OUTPUT.doc

Leave a Reply

Your email address will not be published. Required fields are marked *