ts.seasonal.decomp: Decomposition of seasonal time series

In okgreece/TimeSeries.OBeu: Time Series Analysis 'OpenBudgets.eu'

Description

Decomposition of seasonal time series data using stlm from forecast package. This function is used internally in ts.analysis.

Usage

ts.seasonal.decomp(tsdata, tojson = FALSE)

Arguments

tsdata	The input univariate seasonal time series data
tojson	If TRUE the results are returned in json format, default returns a list

Details

Decomposition of seasonal time series data through arima models is based on stlm from forecast package and returns a list with useful parameters for OBEU.

Value

A list with the following components:

• stl.plot:

  • trend: The estimated trend component

  • seasonal: The estimated seasonal component

  • remainder: The estimated remainder component

  • time: The time of the series was sampled

• stl.general:

  • model.summary The summary object of the arima model to use in forecast if needed

  • stl.win: An integer vector of length 3 indicating the spans used for the "s", "t", and "l" smoothers

  • stl.degree: An integer vector of length 3 indicating the polynomial degrees for these smoothers

• residuals_fitted:

  • residuals: The residuals of the model (fitted innovations)

  • fitted: The model's fitted values

  • time the time of tsdata

  • line The y=0 line

• compare:

  • arima.order: The Arima order

  • arima.coef: A vector of AR, MA and regression coefficients

  • arima.coef.se: The standard error of the coefficients

  • covariance.coef: The matrix of the estimated variance of the coefficients

  • resid.variance: The MLE of the innovations variance

  • not.used.obs: The number of not used observations for the fitting

  • used.obs: the number of used observations for the fitting

  • loglik: The maximized log-likelihood (of the differenced data), or the approximation to it used

  • aic: The AIC value corresponding to the log-likelihood

  • bic: The BIC value corresponding to the log-likelihood

  • aicc: The second-order Akaike Information Criterion corresponding to the log-likelihood

Author(s)

Kleanthis Koupidis

See Also

ts.analysis, stlm

okgreece/TimeSeries.OBeu documentation built on Sept. 7, 2021, 7:21 p.m.