In this paper, we study the Monte Carlo technique of balanced resampling for bootstrapping finite Markov chains. The balanced sampling method is a technique for improving the efficiency of Monte Carlo simulation. The objective here is to apply this idea to facilitate a reduction in the bootstrap replication size necessary to get approximate confidence intervals for the parameters of interest, such as transition probability and stationary distribution. The relative efficiency of bootstrap algorithm under uniform resampling with respect to balanced resampling is discussed. Some numerical results are also studied.
關聯:
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
