Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. 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

Hi markov chain specialist,

Hope you can give me an answer regarding this trellis diagram that i saw on a book. why in this picture of a general first-order markov chain of 2 states,we should know the prob. of each state at each time?

A general first-order markov chain, can be Time-dependent(non stationary) so Transition prob. can change by time. That's why we have E(time) in this picture at each time. but by having the initial Prob. of each state (P(t=1)), and Transition prob. i can calculate prob. of each state in any given time, so The state probabilities at each time (P(t=2,t=3,...)) are Extra informations. am i right or i ignore something?

enter image description here

pic.Statistics in Volcanology (google books) page 167 MArkov chain

share|improve this question
I appreciate any ideas,thoughts,suggestions,... – Michelle Nov 30 '12 at 9:32

[...] but by having the initial Prob. of each state (P(t=1)), and Transition prob. i can calculate prob. of each state in any given time [...]

That sounds correct. You should be able to use induction and conditioning to deduce this. It has been a while since I've done anything with Markov Chains, so apologies in advance for any poor notation (also my first post ever :D ). The base case for induction should look something like this.

Suppose that we know the initial probabilities as above. Then we have :

$P_1[2] = P(X_2=1|X_1=1)P(X_1=1)+P(X_2=1|X_1=2)P(X_1=2)= S_1\epsilon_{11}[1]+S_2\epsilon_{21}[1],$

which are all known quantities.

I think a simple induction argument should finish it from there.

share|improve this answer
Thank you so much R S. It has been 13 days that i was waiting for a response and i wasn't sure that my understanding from Markov chain is correct. Now i can continue on Hidden Markov chains. thanks so much – Michelle Dec 4 '12 at 9:03
No problem. You should be able to generalize this argument to any Markov chain with finite state space, assuming you know the initial state probabilities (at least that sounds right). – R S Dec 4 '12 at 15:43

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.