I'm currently looking at runs of identical outputs, and looking at the fractions I get back. When I was running through it, I had a feeling I'd come across something similar before, and it would be really useful to be able to use the actual mathematical technique if there is one, but I don't know what I'm looking for. Can anyone point me in the right direction? The idea is as follows:
I have two vectors, for simplicity, they are
{A, B, B, C, C, C}, and {A, A, B, B, C, C}.
I'm looking at them different ways, but really it's:
A=A, B!=A, B=B, C!=B, C=C, C=C,
which gives
1/6, 1/6, 2/6 - the overall fraction of consecutive True statements,
while comparing with the fraction of True statements:
1/4, 1/4, 2/4
and then possibly looking at the difference between the consecutive fractions and the consecutive overall:
1/4 % 1/6 = 1.5
I'm sorry I'm explaining this badly, I hope the example helps. Is there a theory I should look at? Or some rule for weighting in Machine Learning etc?