Displaying 1 result from an estimated 1 matches for "classii".
Did you mean:
classic
2004 Mar 30
1
classification with nnet: handling unequal class sizes
...48: The very nice and general function
CVnn2() to choose the number of hidden units and the amount of weight
decay by an inner cross-validation- with a slight modification to use it
for classification (see below).
My data has 2 classes with unequal size: 45 observations for classI and
116 obs. for classII
With CVnn2 I get the following confusion matrix (%) (average of 10
runs):
predicted
true 53 47
16 84
I had a similar biased confusion matrix with randomForest until I used
the sampsize argument (the same holds for svm until I used the
class.weights argument).
How can I handle this problem of...