2 comments on “Primer on Hidden Markov Models: Part 1

  1. I’ve always found the other method of calculating the steady state probabilities to be pretty interesting also.

    qP = q
    qP = qI
    q(P-I) = 0

    you end up with n simultaneous equations for n variables (plus the constraint that they must sum to 1).

    PS, your sunny/rainy transition probabilities are way off for seattle.

  2. The other method is a lot nicer for getting the exact answer as opposed to an approximation. Raising the matrix to some extreme number is easier to visualize and plug in to MATLAB.

    And you are correct, I wasn’t modeling Seattle. I imagine the probabilities for sunny/rainy would be flipped :P

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s