cptSeqCUSUMerroCheck: Error checking - cptSeqCUSUM

In grundy95/changepoint.forecast: Sequential Changepoint Detection of Forecast Errors

Description

Performs error checking on arguments given to cptSeqCUSUM

Usage

cptSeqCUSUMerroCheck(
  X = X,
  m = m,
  detector = detector,
  gamma = gamma,
  sigma2 = sigma2,
  critValue = critValue,
  alpha = alpha,
  samples = samples,
  npts = npts,
  Class = Class
)

Arguments

X	time series. Can be a numeric vector or a ts object
m	length of training period
detector	character. Type of changepoint detector to use. Choice of "PageCUSUM": Page's CUSUM detector for 2-sided alternative hypothesis "PageCUSUM1": Page's CUSUM detector for 1-sided alternative hypothesis "CUSUM": Original CUSUM detector for 2-sided alternative hypothesis "CUSUM1": Original CUSUM detector for 1-sided alternative hypothesis
gamma	tuning parameter in the weight function. See details below
sigma2	variance of data in training period. Default is NULL and variance is estimated using var() (assumes independence).
critValue	numeric or character: numeric: This will be used as the critical value. Note this is not the raw threshold. 'Lookup': a pre-simulated critical value is used if available. 'Simulate': a critical value is simulated, dependent on scenario this can be time consuming.
alpha	asymptotic type 1 error rate. Not used if critValue is a numeric.
samples	Only used if critValue='Simulate'. Number of sample of Weiner processes used to calculate critical value.
npts	Only used if critValue='Simulate'. Number of points in each sample of a Weiner process used to calculate critical value.
Class	Logical. Return an object of class cptFor.

grundy95/changepoint.forecast documentation built on Dec. 20, 2021, 1:45 p.m.