pcts
Periodically Correlated and Periodically Integrated Time Series
Classes and methods for modelling and simulation of
periodically correlated (PC) and periodically integrated time
series. Compute theoretical periodic autocovariances and related
properties of PC autoregressive moving average models. Some original
methods including Boshnakov & Iqelan (2009)
'pcts' is an R package for modelling periodically correlated and periodically integrated time series.
Installing pcts
Install the latest stable version of
pcts from CRAN:
install.packages("pcts")
You can install the development version of
pcts from Github:
library(remotes)
install_github("GeoBosh/pcts")
Overview
Periodic time series can be created with pcts(). Models are fitted with
fitPM() and several other functions. To obtain periodic properties, such as
sample periodic autocorrelations of periodic time series or theoretical periodic
autocorrelations of periodic models, just call the respective functions (here
autocorrelations() and partialAutocorrelations()) and they will compute the
relevant property depending on the class of the argument, see the examples in
the documentation.
A good place to start is the help topic ?pcts-package. Several datasets are
available for examples and experiments. For example, ?dataFranses1996
contains the data from Franses (1996). The datasets are from classes "mts" or
"ts" (the standard R classes for time series), so can be used without loading
pcts, if desired.