I have two transition matrixes in which the probabilities for the transition between each from state to each to states are recorded. For instance

trans_mat1 is

      s1    s2    s3    
s1    0.23  0.15  0.26
s2    0.82  0.01  0.01
s3    0.27  0.78  0.08

trans_mat2 is

      s1    s2    s3    
s1    0.05  0.66  0.44
s2    0.57  0.70  0.12
s3    0.71  0.01  0.28

These are dummy transition matrixes to show an MWE. I am confused how to check if these two transition matrixes show the same transition pribabilities given that s1, s2, and s3 are same in both matrixes?

Can I treat them as a single probability distribution vector and calculate KL divergence using scipy.stats.entropy function ?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.