This internal function sets the parameter options used for fitting meta-analytical models, commonly to pre-specified default values. It is usually internally called by mvmeta.fit.
mvmeta.control(optim=list(), showiter=FALSE, maxiter=100, initPsi=NULL,
Psifix=NULL,Psicor=0, Scor=0, inputna=FALSE, inputvar=10^4, igls.iter=10,
hessian=FALSE, vc.adj=TRUE,reltol=sqrt(.Machine$double.eps),
set.negeigen=sqrt(.Machine$double.eps))logical. If TRUE, the progress of iterative optimization is shown.
positive interger value. Maximum number of iterations in methods involving optimization procedures.
either a matrix or a vector of its lower triangular elements (with diagonal, taken by column) from which starting values of the parameters of the between-study (co)variance matrix are derived, used in the optimization procedure for likelihood-based random-effects models. If NULL (the default, and recommended), the starting value is created internally through an iterative generalized least square algorithm.
either a matrix or a vector of its lower triangular elements (with diagonal, taken by column) equal or proportional to the between-study (co)variance. Only used when bscov="fixed" or bscov="prop" in mvmeta, and, if not provided, it set internally to a 0 or identity matrix, respectively.
either a scalar, vector or matrix representing the within-study correlation(s) to be inputted when the covariances are not provided, and ignored if they are (see inputcov).
logical. If missing values must be internally inputted. To be used with caution, see inputna.
multiplier for inputting the missing variances, to be passed as an argument to inputna.
number of iteration of the iterative generalized least square algorithm to be run in the hybrid optimization procedure of linkelihood-based models to provide the starting value. See iter.igls.
logical. If TRUE, the Hessian matrix of the parameters estimated in the optimization process is computed and returned. Only applicable to likelihood-based estimation methods. For details, see the info provided in the help pages of the optimizations algorithms and (co)variance structure.
logical. If TRUE, an adjustement to the way the marginal variance part is computed in the variance components estimator is applied. See mvmeta.vc.
relative convergence tolerance in methods involving optimization procedures. The algorithm stops if it is unable to reduce the value by a factor of reltol * (abs(val) + reltol) at a step.
positive value. Value to which negative eigenvalues are to be set in estimators where such method is used to force positive semi-definiteness of the estimated between-study (co)variance matrix.
A list with components named as the arguments.
The control argument of mvmeta is by default passed to mvmeta.fit, which uses its elements as arguments of mvmeta.control.
Many arguments refer to specific fitting procedures. Refer to the help page of the related estimator for details.
The function automatically sets non-default values for some control arguments for optim, unless explicitly set in the list passed to it. Specifically, the function selects fnscale=-1, maxit=maxiter and reltol=reltol, where the latter two are specified by other arguments of this function.
The function is expected to be extended and/or modified at every release of the package mvmeta.
Sera F, Armstrong B, Blangiardo M, Gasparrini A (2019). An extended mixed-effects framework for meta-analysis.Statistics in Medicine. 2019;38(29):5429-5444. [Freely available here].
Gasparrini A, Armstrong B, Kenward MG (2012). Multivariate meta-analysis for non-linear and other multi-parameter associations. Statistics in Medicine. 31(29):3821--3839. [Freely available here].
See mvmeta. See also glm.control. See the help pages of the related fitting functions for details on each parameter. See mvmeta-package for an overview of this modelling framework.
# NOT RUN {
# PRINT THE ITERATIONS (SEE ?optim) AND CHANGE THE DEFAULT FOR STARTING VALUES
model <- mvmeta(cbind(PD,AL)~pubyear,S=berkey98[5:7],data=berkey98,
control=list(showiter=TRUE,igls.iter=20))
# INPUT THE CORRELATION
model <- mvmeta(cbind(y1,y2),S=cbind(V1,V2),data=p53,control=list(Scor=0.5))
# }
Run the code above in your browser using DataLab