ocd_update: Processing a new data point for the 'OCD' class

In ocd: High-Dimensional Multiscale Online Changepoint Detection

Description

This function implements the getData function to perform the online changepoint detection for the 'OCD' class.

Usage

ocd_update(x_new, A, tail, beta, sparsity)

Arguments

x_new	a new data point
A	matrix of tail CUSUMs that will be tracked and updated online
tail	matrix of tail lengths that will be tracked and updated online
beta	a user specified lower bound on the l_2 norm of the vector of change to be detected.
sparsity	a user specified mode parameter. If the vector of change is known to be dense or sparse, then one should set sparsity to 'dense' or 'sparse' accordingly, otherwise, the default choice sparsity='auto' will run the algorithm adaptive to the sparsity level.

Value

a list of

• stat: a vector of the test statistics for the 'OCD' class

• A: the updated A matrix

• tail: the updated tail matrix

References

Chen, Y., Wang, T. and Samworth, R. J. (2020) High-dimensional multiscale online changepoint detection Preprint. arxiv:2003.03668.

ocd documentation built on Oct. 23, 2020, 5:56 p.m.