This program runs a random-scan component-wise Metropolis MCMC algorithm on a spatial point process hardcore model for a fixed number of particles, with initial distribution uniform over the pink region, and with target density (with respect to uniform) proportional to exp(-H), where

H(z_1, z_2, ..., z_N) = A * sum_{i<j} |z_i − z_j| + B * sum_{i<j} (1 / |z_i − z_j|) + C * sum_i (z_i1)

The program accepts the following keyboard inputs (or you can mouse click):

• Use the numbers '0' though '9' to set the animation speed level higher or lower. (Note that 0=frozen, and 1=one-step. Alternatively, use 'f' or 's' or 'o' for faster/slower/one.)
• Use 'A' and 'a' to increase/decrease the value of A, and similarly 'B' and 'b' for B, and 'C' and 'c' for C. (Yes, negative values are allowed.)
• Use 'r' to restart the simulation, or 'z' to just zero the counts. (The initial distribution is always independent uniform placement.)
• Use 'p' and 'm' to increase/decrease the size ("rad") of the proposal increments.
• Use '+' and '−' to increase/decrease the number N of particles (and restart the simulation).
• Use 't' to toggle between (S)ystematic or (R)andom scan type.
• Use 'l' or 'L' to toggle showing a thin red line at the right-most particle.

This program is written by Jeffrey Rosenthal. See also my other JavaScript, my Stochastic Processes book, and my Java Applets.