It depends on the system you are modeling.

For example, if you are modeling some customers coming to an airport
counter, then a natural choice for Markov state is the number of
customers currently waiting in queue and in service, which can be 0,
1, 2, ... , infinity.  This is so-called M/M/1 system.

On the other hand, you can also choose more than one parameter for the
state, say, a pair (x,y).  This is called two-dimensional state space.

In general, reducing the state space as small as possible makes
analysis easier.

Frank Li

[EMAIL PROTECTED] (Linda) wrote in message 
news:<[EMAIL PROTECTED]>...
> Hi there!
> 
> I wonder whether there are any good rule of thumb in choosing Markov states?
> 
> Cheers,
> Linda
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to