Logistic Regression Validation Approach
10 views (last 30 days)
Show older comments
Hi, I am using matlab to run the Logistic Regression. I need to validate the logistic regression model. My approach is I split my data into two groups. 85% of them is for training, and 15% of them is for testing. Now I have model from training data sets. I use the independent variables of test data sets as the inputs for the model, and I got the predicted outputs of the model. Then, I have to compare the predicted outputs and observed outputs. What kind of method here should I use to compare them? MSE? or what? Do you think my approach is right? I've read some paper about goodness of fit. I am not quite sure for this issue. Could you please give me some guide? Thank you.
0 Comments
Answers (0)
See Also
Categories
Find more on Testing Frameworks in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!