Fit Multivariate Meta-Analysis

This function estimates fixed-, random-, or mixed-effects meta-analysis parameters using the estimated coefficients and sampling variance-covariance matrix from each individual fitted using the fitDTVARMxID::FitDTVARMxID() function.

Usage

MetaVARMx(
  object,
  x = NULL,
  alpha_values = NULL,
  alpha_free = NULL,
  alpha_lbound = NULL,
  alpha_ubound = NULL,
  gamma_values = NULL,
  gamma_free = NULL,
  gamma_lbound = NULL,
  gamma_ubound = NULL,
  tau_sqr_d_free = NULL,
  tau_sqr_d_values = NULL,
  tau_sqr_d_lbound = NULL,
  tau_sqr_d_ubound = NULL,
  tau_sqr_l_free = NULL,
  tau_sqr_l_values = NULL,
  tau_sqr_l_lbound = NULL,
  tau_sqr_l_ubound = NULL,
  random = TRUE,
  diag = FALSE,
  effects = TRUE,
  int_meas = FALSE,
  int_dyn = FALSE,
  cov_meas = FALSE,
  cov_dyn = FALSE,
  converged = TRUE,
  grad_tol = 0.01,
  hess_tol = 1e-08,
  vanishing_theta = TRUE,
  theta_tol = 0.001,
  try = 1000,
  ncores = NULL,
  ...
)

Arguments

object

Output of the fitDTVARMxID::FitDTVARMxID() function.

x

An optional list. Each element of the list is a numeric vector of covariates for the mixed-effects model.

alpha_values

Numeric vector. Optional vector of starting values for alpha.

alpha_free

Logical vector. Optional vector of free (TRUE) parameters for alpha.

alpha_lbound

Numeric vector. Optional vector of lower bound values for alpha.

alpha_ubound

Numeric vector. Optional vector of upper bound values for alpha.

gamma_values

Numeric matrix. Optional matrix of starting values for gamma.

gamma_free

Logical matrix. Optional matrix of free (TRUE) parameters for gamma.

gamma_lbound

Numeric matrix. Optional matrix of lower bound values for gamma.

gamma_ubound

Numeric matrix. Optional matrix of upper bound values for gamma.

tau_sqr_d_free

Logical vector indicating free/fixed status of the elements of tau_sqr_d. If NULL, all element of tau_sqr_d are free.

tau_sqr_d_values

Numeric vector with starting values for tau_sqr_d. If NULL, defaults to a vector of ones.

tau_sqr_d_lbound

Numeric vector with lower bounds for tau_sqr_d. If NULL, no lower bounds are set.

tau_sqr_d_ubound

Numeric vector with upper bounds for tau_sqr_d. If NULL, no upper bounds are set.

tau_sqr_l_free

Logical matrix indicating which strictly-lower-triangular elements of tau_sqr_l are free. Ignored if diag = TRUE.

tau_sqr_l_values

Numeric matrix of starting values for the strictly-lower-triangular elements of tau_sqr_l. If NULL, defaults to a null matrix.

tau_sqr_l_lbound

Numeric matrix with lower bounds for tau_sqr_l. If NULL, no lower bounds are set.

tau_sqr_l_ubound

Numeric matrix with upper bounds for tau_sqr_l. If NULL, no upper bounds are set.

random

Logical. If random = TRUE, estimates random effects. If random = FALSE, tau_sqr is a null matrix.

diag

Logical. If diag = TRUE, tau_sqr is a diagonal matrix. If diag = FALSE, tau_sqr is a symmetric matrix.

effects

Logical. If effects = TRUE, include estimates of the dynamic effects matrix, if available. If effects = FALSE, exclude estimates of the dynamic effects matrix.

int_meas

Logical. If int_meas = TRUE, include estimates of the measurement intercept vector, if available. If int_meas = FALSE, exclude estimates of the measurement intercept vector.

int_dyn

Logical. If int_dyn = TRUE, include estimates of the dynamic process intercept vector, if available. If int_dyn = FALSE, exclude estimates of the dynamic process intercept vector.

cov_meas

Logical. If cov_meas = TRUE, include estimates of the measurement error covariance matrix, if available. If cov_meas = FALSE, exclude estimates of the measurement error covariance matrix.

cov_dyn

Logical. If cov_dyn = TRUE, include estimates of the process noise covariance matrix, if available. If cov_dyn = FALSE, exclude estimates of the process noise covariance matrix.

converged

Logical. Only include converged cases.

grad_tol

Numeric scalar. Tolerance for the maximum absolute gradient if converged = TRUE.

hess_tol

Numeric scalar. Tolerance for Hessian eigenvalues; eigenvalues must be strictly greater than this value if converged = TRUE.

vanishing_theta

Logical. Test for measurement error variance going to zero if converged = TRUE.

theta_tol

Numeric. Tolerance for vanishing theta test if converged and theta_tol are TRUE.

try

Positive integer. Number of extra optimization tries.

ncores

Positive integer. Number of cores to use.

...

Additional arguments to pass to OpenMx::mxTryHard().

References

Cheung, M. W.-L. (2015). Meta-analysis: A structural equation modeling approach. Wiley. doi:10.1002/9781118957813

Neale, M. C., Hunter, M. D., Pritikin, J. N., Zahery, M., Brick, T. R., Kirkpatrick, R. M., Estabrook, R., Bates, T. C., Maes, H. H., & Boker, S. M. (2015). OpenMx 2.0: Extended structural equation and statistical modeling. Psychometrika, 81(2), 535–549. doi:10.1007/s11336-014-9435-8

See also

Other Meta-Analysis of VAR Functions: Meta()

Author

Ivan Jacob Agaloos Pesigan