
METROPOLIS–HASTIN G S ALGORIT H MS FOR BAYESIAN INFERENCE 269
Alpha = 0.1
Iteration
Value
0 2000 6000 10000
−2 0 2
0 20 40 60 80 100
0.0 0.8
Empirical density
Value
Density
0 2000 6000 10000
−3 1 4
0 20 40 60 80 100
0.0 0.8
Empirical density
Value
Density
Alpha = 100
Iteration
Value
0 2000 6000 10000
−3 0
0 20 40 60 80 100
0.0 0.8
Empirical density
Value
Density
Figure 9.6 Output from the Metropolis sampler given in Figure 9.5. The top row shows the
result of running the chain with α = 0.1, corresponding to a chain that is too cold. The
middle row shows the results for ...