Learn R Programming

⚠️There's a newer version (2.4.1) of this package.Take me there.

costat (version 1.1-1)

Time series costationarity determination and tests of stationarity.

Description

Contains functions that can determine whether a time series is second-order stationary or not (and hence evidence for locally stationarity). Given two non-stationary series (i.e. locally stationary series) this package can then discover time-varying linear combinations that are second-order stationary.

Copy Link

Version

Install

install.packages('costat')

Monthly Downloads

264

Version

1.1-1

License

GPL-2

Maintainer

Guy Nason

Last Published

August 31st, 2010

Functions in costat (1.1-1)

Find costationary time series, compute time-localized autocovariance, time-localized cross-covariance, time-localized spectrum.

Compute raw cross wavelet periodogram (not intended for casual use)

Plots solutions that are identified by findstysols

Computes a Linear Combination Test Statistics

Perform a series of stationarity tests on a time series at different spans and locations.

Concatenate a set of solution results into one set

Graphical aid for detecting clustering in optimization solutions.

Log-returns time series of the SP500 and FTSE100 indices

Particular section of SP500 log-returns series.

Compute evolutionary wavelet cross spectrum from two series.

Convert wavelet coefficients for two time-varying functions into two functions with respect to time.

Perform bootstrap stationarity test for time series

Particular section of FTSE log-return series.

Plot the results of a multiple stationarity test on a time series

Produces plots from output of findstysol that attempt to group different solutions.

Computes localized (wavelet) autocovariance function

Compute p-value for parametric Monte Carlo test and optionally plot test statistic values

Given two time series find some time-varying linear combinations that are stationary.

Compute the time-localized (unconditional) variance for a time series

A test statistic for stationarity

Combine two time series using a time-varying linear combination.

Compute the time-localized cross-autocovariance of two time series