boiwsa (version 1.1.4)

find_outliers: Detect additive outliers in weekly time series

Description

Detects additive outliers (AOs) using a regression-based t-statistic search procedure following Findley et al. (1998). The function operates on a detrended series, where the trend is estimated using supsmu. Optional holiday and trading-day regressors can be included. If the number of Fourier (trigonometric) terms is not supplied via my.k_l, it is selected automatically by minimizing AICc over a grid of yearly and monthly Fourier terms.

Usage

find_outliers(
  x,
  dates,
  out.tolerance = 3.8,
  my.AO.list = NULL,
  H = NULL,
  my.k_l = NULL,
  method = "additive"
)

Value

A list with the following components:

ao

Vector of class "Date" containing detected additive outlier dates, or NULL if none are detected.

my.k_l

Numeric vector c(k, l) giving the number of yearly and monthly Fourier terms used in the regression.

Arguments

x

Numeric vector containing the observed weekly time series.

dates

A vector of class "Date" corresponding to the observation dates.

out.tolerance

Numeric. Absolute t-statistic threshold used for AO inclusion. Defaults to 3.8.

my.AO.list

Optional vector of class "Date" specifying pre-defined AO dates. These dates are included in the regression and excluded from the forward search.

H

Optional matrix of holiday and trading-day regressors with nrow(H) = length(x).

my.k_l

Optional numeric vector of length two specifying the number of yearly and monthly Fourier harmonics c(k, l). If NULL, my.k_l is selected automatically by AICc.

method

Character string specifying the decomposition type. Either "additive" or "multiplicative". If "multiplicative", the series is log-transformed prior to detrending. Defaults to "additive".

References

Findley, D.F., Monsell, B.C., Bell, W.R., Otto, M.C. and Chen, B.C. (1998). New capabilities and methods of the X-12-ARIMA seasonal-adjustment program. Journal of Business and Economic Statistics, 16(2), 127--152.

Examples

# \donttest{
#Not run:
# Searching for additive outliers in Gasoline data
data(gasoline.data)
ao_list=find_outliers(x=gasoline.data$y,dates = gasoline.data$date)# }