In the latest version of
meboot (v 1.4-8)on CRAN, the function
mebootSpearwas introduced. Below is a gentle introduction to its capabilities and a link to a reference paper with further applications to improved Monte Carlo simulations.
The desired properties from the original maximum entropy bootstrap function
mebootwere retained, while incorporating the additional argument
setSpearman. The original function created bootstrap replicates with unit rank-correlations to the original time-series,
setSpearmanrelaxes this condition.
The following example will demonstrate the
mebootSpearrank-correlation results from the average of 1,000 bootstrap replicates of the
output <- mebootSpear(AirPassengers, setSpearman = 0, xmin = 0)$rowAvg
cor(output, AirPassengers, method = "spearman")
The following paper is available with additional examples and R-code:
Vinod, Hrishikesh D. and Viole, Fred, Arbitrary Spearman’s Rank Correlations in Maximum Entropy Bootstrap and Improved Monte Carlo Simulations (June 7, 2020). Available at SSRN: https://ssrn.com/abstract=3621614