Simulation Comparison of CBB and GSBB in Overall Mean Estimation Problem for PC Time Series

In the chapter the performance comparison in the simulation study of the block bootstrap methods that can be used in the problem of the overall mean estimation of a PC time series is presented. Two block bootstrap techniques are considered: the Circular Block Bootstrap and the circular version of the Generalized Seasonal Block Bootstrap. The actual coverage probabilities of the bootstrap equal-tailed confidence intervals are calculated for a wide range of the block length choices and a few sample sizes. Moreover, the optimal values of the block lengths are pointed. In the most of the considered cases performance of CBB and GSBB is very comparable.