Constructs the global or contemporaneous conditional independence graph (CIG) of the VAR(1) model, as implied by the partial correlations.
● Data Source:
CranContrib
● Keywords:
● Alias: CIGofVAR1
●
0 images
|
Converts an object of the longitudinal -class into a 3-dim array (containing time-series data of multiple individuals).
● Data Source:
CranContrib
● Keywords:
● Alias: longitudinal2array
●
0 images
|
Sample data from a VAR(1) model.
● Data Source:
CranContrib
● Keywords:
● Alias: dataVAR1
●
0 images
|
Function that calculates for each variate various statistics from a sparse VAR(1) model
● Data Source:
CranContrib
● Keywords:
● Alias: nodeStatsVAR1
●
0 images
|
Ridge maximum likelihood estimation of vector auto-regressive processes and supporting functions for their exploitation. Currently, it includes:
● Data Source:
CranContrib
● Keywords: package
● Alias: ragt2ridges, ragt2ridges-package
●
0 images
|
Evaluation of the (minus) leave-one-out cross-validated log-likelihood of the VAR(1) model for given choices of the ridge penalty parameters (λ_a and λ_{ω} for the regression coefficient matrix mathbf{A} and the inverse error covariance matrix mathbf{Ω}_{varepsilon} (=mathbf{Σ_{varepsilon}^{-1}}), respectively). The functions also works with a (possibly) unbalanced experimental set-up. The VAR(1)-process is assumed to have mean zero.
● Data Source:
CranContrib
● Keywords:
● Alias: loglikLOOCVVAR1
●
0 images
|
Evaluates the leave-one-out cross-validated log-likelihood of the VAR(1) model for a given grid of the ridge penalty parameters (λ_a and λ_{ω} for the regression coefficient matrix mathbf{A} and the inverse error covariance matrix mathbf{Ω}_{varepsilon} (=mathbf{Σ_{varepsilon}^{-1}}), respectively). The result is plotted as a contour plot, which facilitates the choice of optimal penalty parameters. The functions also works with a (possibly) unbalanced experimental set-up. The VAR(1)-process is assumed to have mean zero.
● Data Source:
CranContrib
● Keywords:
● Alias: loglikLOOCVcontourVAR1
●
0 images
|
Automatic penalty parameter selection for the VAR(1) model through maximization of the leave-one-out cross-validated (LOOCV) log-likelihood.
● Data Source:
CranContrib
● Keywords:
● Alias: optPenaltyVAR1
●
0 images
|
Plot of time series data. Per variate and individual a line connecting the observations at each time point is plotted.
● Data Source:
CranContrib
● Keywords:
● Alias: plotVAR1data
●
0 images
|
Generates regression coefficient matrices of the VAR(1) with various type of topologies
● Data Source:
CranContrib
● Keywords:
● Alias: createA
●
0 images
|