| Type: | Package |
| Title: | Matrix Skew-T Parameter Estimation |
| Version: | 0.1.5 |
| Author: | Michael P.B. Gallaugher, Paul D. McNicholas |
| Maintainer: | Michael P.B. Gallaugher <gallaump@mcmaster.ca> |
| Description: | Performs matrix skew-t parameter estimation, Gallaugher and McNicholas (2017) <doi:10.1002/sta4.143>. |
| License: | GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
| Encoding: | UTF-8 |
| LazyData: | true |
| RoxygenNote: | 6.1.1 |
| NeedsCompilation: | no |
| Packaged: | 2019-07-25 18:00:07 UTC; michaelgallaugher |
| Repository: | CRAN |
| Date/Publication: | 2019-07-28 10:00:06 UTC |
Matrix Skew t Parameter Estimation
Description
Performs paramter estimation for the matrix variate skew-t distribution using an ECM algorithm.
Usage
Fit_Skewt(X, Tol = 0.001, max_iter = 1000)
Arguments
X |
A list of matrices of the same size |
Tol |
The tolerance of the ECM algorithm. Defaults to 0.001 |
max_iter |
The maximum number of iterations. Defaults to 1000 |
Value
Returns a list with elements M (the estimate of the location), A (the estimate of the skewness), nu (the estimate of the degrees of freedom), Sigma (the estimate of Sigma), Psi (the estimate of Psi), loglik (a vector of log likelihood values), flag (returns TRUE if a numerical issue occured, FALSE otherwise).
Examples
data(SimX)
Fit_st<-Fit_Skewt(SimX)
Simulated Data
Description
This is a simulated dataset with 100 observations from 4 by 3 matrix skew-t distribution.
Usage
data(SimX)
Format
An object of class list of length 100.