Hello,
I'm looking for an information criterion (similar to AIC[1]) for model selection, where model output is a binary prediction.
For example, suppose we have to compare two models, M1 and M2. We know that M1 contains 2 parameters and M2 contains 4 parameters. Since I am not mathematician, I will be very happy if someone can show me the actual calculations using the following summary table that lists the observed (O) and predicted outcomes in CSV format.
#,O,M1,M2
1,1,1,0
2,1,0,1
3,1,1,1
4,0,0,1
5,0,1,0
6,0,0,0
7,1,1,0
8,1,1,1
9,1,0,1
10,0,0,0
Thank you very much,
David
