karma.transform: Find transformation steps required for stationarity.

In snarf-snarf/karma: Complementary tools for automated time-series machine learning.

Description

Find transformation steps required for stationarity.

Usage

karma.transform(yt, stdout = T, autolog = T, autodiffs = 1,
  autolags = F, r2_criterion = T)

Arguments

yt	A univariate time-series vector; type <numeric> or <ts>.
stdout	Option to print out all search diagnostics; <logical>.
autolog	Logarithmic search flag. Indicates whether log-transformations on the input series will be part of the search.
autodiffs	Differencing search flag. Indicates whether differencing on the input series will be part of the search.
autolags	Flag T/F indicating whether or not to set lags automatically as a function of the length of the series.
r2_criterion	Flag T/F incidating whether or not to use adjusted R-square as an ADF model selection criterion. When FALSE, the simplest possible stationarity transformation will be preferred.

Value

Object of class "karma.transform".

See Also

tseries, forecast

Examples

# Apply ADF test and print out diagnostics:
stationarity.options <- karma.transform(WWWusage, stdout = F, autolog = F, autodiffs = 1)
print(stationarity.options$model)  # best fitted model type
print(stationarity.options$diffs)  # best degree of differencing
print(stationarity.options$log)    # best use of logarithmic transformation 

snarf-snarf/karma documentation built on May 24, 2019, 7:19 a.m.