Metropolis-Hastings algorithm
Metropolis-Hastings algorithm
Metropolis-Hastings algorithm
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
General <strong>Metropolis</strong>-<strong>Hastings</strong> <strong>algorithm</strong><br />
• Sample values from target distribution generated by taking a random<br />
walk through the multidimensional parameter space.<br />
– Begins at arbitrary point, specified by user, where P(θ) is non-zero.<br />
– At each time step:<br />
• Move to new position in parameter space is proposed.<br />
• Decide whether or not to accept move to new position.<br />
– Proposal distributions can be of various forms.<br />
• Goal is to efficiently explore regions of parameter space where P(θ)<br />
has greatest mass.<br />
• Simplest case: proposal distribution is normal, centered on current<br />
position.<br />
• Proposed move will typically ybe near present position, with probability<br />
of more distant positions decreasing with distance:<br />
0.4<br />
0.35<br />
0.3<br />
025 0.25<br />
P()<br />
0.2<br />
0.15<br />
0.1<br />
0.05<br />
0<br />
-3 -2 -1 0 1 2 3