Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I encountered the problem here(Hidden Markov Chain)

It is like this:

The task is to compute, given the parameters of the model, the probability of a particular output sequence(observed sequence). This requires summation over all possible state sequences: The probability of observing a sequence(output sequence)

enter image description here

of length L is given by

enter image description here (*)

where the sum runs over all possible hidden-node sequences

enter image description here

For more specific information on the related information, refer to here

My problem is:

How the (*) equation can be derived?

It seems to be according to Total Probability Theorem. But this does not make sense to me.

share|cite|improve this question
Does $P(Y) = \sum_X P(Y \; X) $ makes sense to you? – leonbloy Sep 27 '11 at 15:46

Your notations are awful but this is indeed nothing else than the law of total probabilities: you consider two discrete random variables $X$ and $Y$ defined on the same probability space with values in sets $E$ and $F$ respectively and you are asserting that for every $y$ in $F$, $$ \mathrm P(Y=y)=\sum\limits_{x\in E}\mathrm P(Y=y\mid X=x)\mathrm P(X=x). $$ Compare with this for $A=[Y=y]$.

share|cite|improve this answer
Do you mean that $E$ is countable or finite? – Ilya Sep 27 '11 at 17:23

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.