DLResiduals
(Package: ltsa) :
Prediction residuals
The Durbin-Levison algorithm is used to compute the one-step prediction residuals.
● Data Source:
CranContrib
● Keywords: ts
● Alias: DLResiduals
●
0 images
|
TrenchLoglikelihood
(Package: ltsa) :
Loglikelihood function of stationary time series
The Trench matrix inversion algorithm is used to compute the exact concentrated loglikelihood function.
● Data Source:
CranContrib
● Keywords: ts
● Alias: TrenchLoglikelihood
●
0 images
|
tacvfARMA
(Package: ltsa) :
theoretical autocovariance function (acvf) of ARMA
The theoretical autocovariance function of ARMA(p,q) process is computed. This is more useful in some situations than the built-in R function ARMAacf . See Details.
● Data Source:
CranContrib
● Keywords: ts
● Alias: tacvfARMA
●
0 images
|
Linear time series modelling. Methods are given for loglikelihood computation, forecasting and simulation.
● Data Source:
CranContrib
● Keywords: package, ts
● Alias: ltsa, ltsa-package
●
0 images
|
DLAcfToAR
(Package: ltsa) :
Autocorrelations to AR parameters
Given autocorrelations at lags 1,...,n the AR parameters corresponding to the AR coefficients, partial autocorrelations (pacf) and standarized minimum-mean-square predictor variance (sigsqk) are computed. Can also be used as a test for valid acf sequence.
● Data Source:
CranContrib
● Keywords: ts
● Alias: DLAcfToAR
●
0 images
|
SimGLP
(Package: ltsa) :
Simulate GLP given innovations
Simulates a General Linear Time Series that can have nonGaussian innovations. It uses the FFT so it is O(N log(N)) flops where N=length(a) and N is assumed to be a power of 2. The R function convolve is used which implements the FFT.
● Data Source:
CranContrib
● Keywords: datagen, ts
● Alias: SimGLP
●
0 images
|
is.toeplitz
(Package: ltsa) :
test if argument is a symmetric Toeplitz matrix
Auxilary function, used to validate the input of TrenchInverse
● Data Source:
CranContrib
● Keywords: array, ts
● Alias: is.toeplitz
●
0 images
|
The innovation variance is estimated using a high order AR approximation determined by the AIC or by using Kolmogoroff's formula with a smoothed periodogram. Default is AR.
● Data Source:
CranContrib
● Keywords: ts
● Alias: innovationVariance
●
0 images
|
TrenchForecast
(Package: ltsa) :
Minimum Mean Square Forecast
Given time series of length n+m, the forecasts for lead times k=1,...,L are computed starting with forecast origin at time t=n and continuing up to t=n+m. The input time series is of length n+m. For purely out-of-sample forecasts we may take n=length(z). Note that the parameter m is inferred using the fact that m=length(z)-n.
● Data Source:
CranContrib
● Keywords: ts
● Alias: TrenchForecast
●
0 images
|
DLLoglikelihood
(Package: ltsa) :
Durbin-Levinsion Loglikelihood
The Durbin-Levinsion algorithm is used for the computation of the exact loglikelihood function.
● Data Source:
CranContrib
● Keywords: ts
● Alias: DLLoglikelihood
●
0 images
|