Joint block bootstrap for generating probabilistic base forecasts that take into account the correlation between different time series and temporal aggregation order at the same time (Girolimetto et al. 2023).
boot_ct(fit, boot_size, m, h = 1, seed = NULL)A list of \(n\) elements. Each elements is a list with the \((k^\ast+m)\)
base forecast models ordered as [lowest_freq' ... highest_freq']' of the cross-sectional
series. It is important to note that the models must have the simulate()
function available and implemented as with the package forecast, with
the following mandatory parameters: object, innov, future, and nsim.
The number of bootstrap replicates.
Highest available sampling frequency per seasonal cycle (max. order of temporal aggregation, \(m\)), or a subset of \(p\) factors of \(m\).
Forecast horizon for the most temporally aggregated series.
An integer seed.
A list with two elements: the seed used to sample the errors and a (\(boot\_size\times hn(k^\ast+m)\)) matrix
Girolimetto, D., Athanasopoulos, G., Di Fonzo, T., & Hyndman, R. J. (2023), Cross-temporal Probabilistic Forecast Reconciliation, doi:10.48550/arXiv.2303.17277 .