MOSUM wrapper — Moving Sum

Wraps the mosum package for moving-sum-based changepoint detection, either at a single bandwidth or (with multiscale = TRUE) across a bandwidth grid with localised pruning.

Usage

mosum_wrapper(x, G = NULL, multiscale = FALSE, seed = NULL, ...)

Arguments

x

A numeric vector.

G

Bandwidth. If NULL, automatically selected (min(n/10, 100), but never below 2, for the single-bandwidth procedure; the engine's default bandwidth grid for the multiscale procedure). A bandwidth of 1 leaves the engine's local variance estimate undefined, so the automatic choice is floored at 2.

multiscale

Logical. Use the multiscale MOSUM procedure (mosum::multiscale.localPrune()) instead of a single bandwidth? Defaults to FALSE.

seed

Optional seed for reproducibility.

...

Additional arguments passed to mosum::mosum() or mosum::multiscale.localPrune().

Value

A ggcpt object.

References

Eichinger B, Kirch C (2018). “A MOSUM Procedure for the Estimation of Multiple Random Change Points.” Bernoulli, 24(1), 526–564. doi:10.3150/16-BEJ887 .

See also

Other changepoint engines: bcp_wrapper(), beast_wrapper(), bfast_wrapper(), binsegrcpp_wrapper(), bocpd_wrapper(), cpm_wrapper(), cpop_wrapper(), cpt_wrapper(), decafs_wrapper(), ecp_wrapper(), envcpt_wrapper(), esac_wrapper(), fabisearch_wrapper(), fastcpd_wrapper(), fcov_wrapper(), fmean_wrapper(), fpop_wrapper(), geomcp_wrapper(), hdcov_wrapper(), hdreg_wrapper(), idetect_wrapper(), inspect_wrapper(), kcp_wrapper(), kwc_wrapper(), mcp_wrapper(), network_wrapper(), not_wrapper(), npmojo_wrapper(), nsp_wrapper(), ocd_wrapper(), pilliat_wrapper(), segmented_wrapper(), smuce_wrapper(), sn_wrapper(), strucchange_wrapper(), taylor_wrapper(), tguh_wrapper(), trend_wrapper(), var_wrapper(), wbs2_wrapper(), wbs_wrapper(), wbsts_wrapper()

Examples

set.seed(2026)
x <- c(rnorm(100), rnorm(100, 3))
mosum_wrapper(x, G = 20)$changepoints
#> # A tibble: 1 × 2
#>      cp cp_value
#>   <int>    <dbl>
#> 1   100    0.369
mosum_wrapper(x, multiscale = TRUE)$changepoints
#> # A tibble: 1 × 2
#>      cp cp_value
#>   <int>    <dbl>
#> 1   100    0.369