impute_covariance_matrix {clubSandwich}R Documentation

Impute a block-diagonal covariance matrix

Description

impute_covariance_matrix calculates a block-diagonal covariance matrix, given the marginal variances, the block structure, and an assumed correlation structure. Can be used to create compound-symmetric structures, AR(1) auto-correlated structures, or combinations thereof.

Usage

impute_covariance_matrix(
  vi,
  cluster,
  r,
  ti,
  ar1,
  smooth_vi = FALSE,
  subgroup = NULL,
  return_list = identical(as.factor(cluster), sort(as.factor(cluster))),
  check_PD = TRUE
)

Arguments

vi

Vector of variances

cluster

Vector indicating which effects belong to the same cluster. Effects with the same value of 'cluster' will be treated as correlated.

r

Vector or numeric value of assumed constant correlation(s) between effect size estimates from each study.

ti

Vector of time-points describing temporal spacing of effects, for use with auto-regressive correlation structures.

ar1

Vector or numeric value of assumed AR(1) auto-correlation(s) between effect size estimates from each study. If specified, then ti argument must be specified.

smooth_vi

Logical indicating whether to smooth the marginal variances by taking the average vi within each cluster. Defaults to FALSE.

subgroup

Vector of category labels describing sub-groups of effects. If non-null, effects that share the same category label and the same cluster will be treated as correlated, but effects with different category labels will be treated as uncorrelated, even if they come from the same cluster.

return_list

Optional logical indicating whether to return a list of matrices (with one entry per block) or the full variance-covariance matrix.

check_PD

Optional logical indicating whether to check whether each covariance matrix is positive definite. If TRUE (the default), the function will display a warning if any covariance matrix is not positive definite.

Details

A block-diagonal variance-covariance matrix (possibly represented as a list of matrices) with a specified structure. The structure depends on whether the r argument, ar1 argument, or both arguments are specified. Let v_{ij} denote the specified variance for effect i in cluster j and C_{hij} be the covariance between effects h and i in cluster j.

If smooth_vi = TRUE, then all of the variances within cluster j will be set equal to the average variance of cluster j, i.e.,

v'_{ij} = \frac{1}{n_j} \sum_{i=1}^{n_j} v_{ij}

for i=1,...,n_j and j=1,...,k.

Value

If cluster is appropriately sorted, then a list of matrices, with one entry per cluster, will be returned by default. If cluster is out of order, then the full variance-covariance matrix will be returned by default. The output structure can be controlled with the optional return_list argument.

Examples

library(metafor)

# Constant correlation
data(SATcoaching)
V_list <- impute_covariance_matrix(vi = SATcoaching$V, cluster = SATcoaching$study, r = 0.66)
MVFE <- rma.mv(d ~ 0 + test, V = V_list, data = SATcoaching)
conf_int(MVFE, vcov = "CR2", cluster = SATcoaching$study)


[Package clubSandwich version 0.5.6 Index]