Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Optimal scaling of the random walk Metropolis
T2 - general criteria for the 0.234 acceptance rule
AU - Sherlock, Christopher
PY - 2013/3
Y1 - 2013/3
N2 - Scaling of proposals for Metropolis algorithms is an important practical problem in MCMC implementation. Analyses of the random walk Metropolis for high dimensional targets with specific functional forms have shown that in many cases the optimal scaling is achieved when the acceptance rate is approximately 0.234, but that there are exceptions. We present a general set of sufficient conditions which are invariant to orthonormal transformation of the co-ordinate axes and which ensure that the limiting optimal acceptance rate is 0.234. The criteria are shown to hold for the joint distribution of successive elements of a stationary p-th order multivariate Markov process.
AB - Scaling of proposals for Metropolis algorithms is an important practical problem in MCMC implementation. Analyses of the random walk Metropolis for high dimensional targets with specific functional forms have shown that in many cases the optimal scaling is achieved when the acceptance rate is approximately 0.234, but that there are exceptions. We present a general set of sufficient conditions which are invariant to orthonormal transformation of the co-ordinate axes and which ensure that the limiting optimal acceptance rate is 0.234. The criteria are shown to hold for the joint distribution of successive elements of a stationary p-th order multivariate Markov process.
KW - Random walk Metropolis
KW - optimal scaling
KW - optimal acceptance rate
U2 - 10.1239/jap/1363784420
DO - 10.1239/jap/1363784420
M3 - Journal article
VL - 50
SP - 1
EP - 15
JO - Journal of Applied Probability
JF - Journal of Applied Probability
IS - 1
ER -