covariance_types {mmrm}R Documentation

Covariance Types

Description

[Maturing]

Usage

cov_types(
  form = c("name", "abbr", "habbr"),
  filter = c("heterogeneous", "spatial")
)

Arguments

form

(character)
covariance structure type name form. One or more of "name", "abbr" (abbreviation), or "habbr" (heterogeneous abbreviation).

filter

(character)
covariance structure type filter. One or more of "heterogeneous" or "spatial".

Value

A character vector of accepted covariance structure type names and abbreviations.

Abbreviations for Covariance Structures

Common Covariance Structures:

Structure Description Parameters (i,j)(i, j) element
ad Ante-dependence mm σ2k=ij1ρk\sigma^{2}\prod_{k=i}^{j-1}\rho_{k}
adh Heterogeneous ante-dependence 2m12m-1 σiσjk=ij1ρk\sigma_{i}\sigma_{j}\prod_{k=i}^{j-1}\rho_{k}
ar1 First-order auto-regressive 22 σ2ρij\sigma^{2}\rho^{\left \vert {i-j} \right \vert}
ar1h Heterogeneous first-order auto-regressive m+1m+1 σiσjρij\sigma_{i}\sigma_{j}\rho^{\left \vert {i-j} \right \vert}
cs Compound symmetry 22 σ2[ρI(ij)+I(i=j)]\sigma^{2}\left[ \rho I(i \neq j)+I(i=j) \right]
csh Heterogeneous compound symmetry m+1m+1 σiσj[ρI(ij)+I(i=j)]\sigma_{i}\sigma_{j}\left[ \rho I(i \neq j)+I(i=j) \right]
toep Toeplitz mm σij+1\sigma_{\left \vert {i-j} \right \vert +1}
toeph Heterogeneous Toeplitz 2m12m-1 σiσjρij\sigma_{i}\sigma_{j}\rho_{\left \vert {i-j} \right \vert}
us Unstructured m(m+1)/2m(m+1)/2 σij\sigma_{ij}

where ii and jj denote ii-th and jj-th time points, respectively, out of total mm time points, 1i,jm1 \leq i, j \leq m.

Note

The ante-dependence covariance structure in this package refers to homogeneous ante-dependence, while the ante-dependence covariance structure from SAS ⁠PROC MIXED⁠ refers to heterogeneous ante-dependence and the homogeneous version is not available in SAS.

For all non-spatial covariance structures, the time variable must be coded as a factor.

Spatial Covariance structures:

Structure Description Parameters (i,j)(i, j) element
sp_exp spatial exponential 22 σ2ρdij\sigma^{2}\rho^{-d_{ij}}

where dijd_{ij} denotes the Euclidean distance between time points ii and jj.

See Also

Other covariance types: as.cov_struct(), cov_struct()


[Package mmrm version 0.3.12 Index]