Random-Walk Metropolis (MCMC) Java Applet
This is a simulation of the Random-Walk Metropolis MCMC algorithm.
(Updated: see the new scalable version.)
This applet runs a simple (random-walk) Metropolis MCMC algorithm on
a simple target distribution (the blue bars) supported on just a few
points (default=6). The black bars represent the chain's empirical
distribution; over time, they should converge in height to the blue
bars, thus illustrating convergence of the Metropolis algorithm to
its target distribution.
The applet accepts the following keyboard inputs. (You may need to
"click" on the applet first.)
Use the numbers '0' though '9' to set the animation speed level higher
Use 'r' to restart the simulation, or 'z' to just zero the empirical count,
or 's' to toggle whether to show the empirical distribution.
Use '>' and '<' to increase/decrease the target probability of state 2
(and restart the simulation).
Use '+' and '-' to increase/decrease the number of states (and restart
Use 'p' and 'm' to increase/decrease the current value of Gamma, the
spread of the (uniform) proposal distribution (default=1).
Applet by Jeffrey S. Rosenthal
[Return to my Applets Page / Home