Learn R Programming

mixmeta (version 1.2.0)

mixmetaObject: mixmeta Objects

Description

An object returned by the mixmeta function, inheriting from class "mixmeta", and representing a fitted univariate or multivariate meta-analytical model.

Arguments

Value

Objects of class "mixmeta" are lists with defined components. Dimensions of such components may refer to \(k\) outcome parameters, \(p\) fixed-effects and \(q\) random-effects predictors, \(m\) groups and \(n\) units used for fitting the model (the latter can be different from those originally selected due to missing). Depending on the type of meta-analytical model, the following components can bu included in a legitimate mixmeta object:

coefficients

a \(kp\)-dimensional vector of the fixed-effects coefficients.

vcov

estimated \(kp \times kp\) (co)variance matrix of the fixed-effects coefficients.

Psi

the estimated \(kq \times kq\) random-effects (co)variance matrix, or a list of matrices for multilevel models. Only for random-effects models.

residuals

a \(n\)-dimensional vector (for univariate models) or \(n \times k\) matrix (for multivariate models) of residuals, that is observed minus fitted values.

fitted.values

a \(n\)-dimensional vector (for univariate models) or \(n \times k\) matrix (for multivariate models) of fitted mean values.

df.residual

the residual degrees of freedom.

rank

the numeric rank of the fixed-effects part of the fitted model.

logLik

the (restricted) log-likelihood of the fitted model. Set to NA for non-likelihood models.

converged, niter

for models with iterative estimation methods, logical scalar indicating if the algorithm eventually converged and number or iterations, respectively.

par

parameters estimated in the optimization process when using likelihood-based estimators. These correspond to trasformations of entries of the random-effects (co)variance matrix, dependent on chosen (co)variance structure. For multilevel models, the vector includes the parameters of multiple matrices. Returned also for full (R)IGLS optimization, even if not directly used. See also the mixmeta.ml for details.

hessian

Hessian matrix of the estimated parameters in par above, only returned if hessian=TRUE in mixmeta.control. See the related optimizations algorithms for details.

dim

list with the following components: k (scalar, number of outcome parameters), n (scalar, number of units included in estimation, which could be lower than the total number in the presence of missing values), m (scalar, number of outer-level groups), p (scalar, number of fixed-effects predictors), q (scalar or vector,number of random-effects predictors).

df

list with the following scalar components: nall (number of observations used for estimation, excluding missing values), nobs (equal to nall, minus the number of fixed-effects coefficients in REML models), fixed (number of estimated fixed-effects coefficients), random (number of estimated random-effects (co)variance terms).

lab

list with the following label vectors: k for the outcome parameters, and p and q for the fixed and random-effects predictors, respectively (including intercept). The last one can be a list for multilevel models.

S

a \(n \times k(k+1)/2\) matrix, where each row represents the vectorized entries of the lower triangle of the related within-unit (co)variance error matrix, taken by column. See mixmeta.

call

the function call.

formula

the formula for the fixed-effects part of the model. See mixmetaFormula.

model

the model frame used for fitting. Reported if model=TRUE in mixmeta. See model.frame.

terms

the terms object representing the fixed-effects part of the fitted model.

contrasts

(where relevant) the contrasts used.

xlevels

(where relevant) a record of the levels of the factors used in fitting.

na.action

(where relevant) information returned by model.frame on the special handling of NAs. See info on missing values.

method

the estimation method.

random

the formula (or list of formulae for multilevel models) for the random-effects part of the model. See mixmetaFormula.

bscov

a string defining the random-effects (co)variance structure in likelihood based models. See model.frame.mixmeta.

control

a list with the values of the control arguments used, as returned by mixmeta.control.

Methods

A number of methods functions are available for mixmeta objects, most of them common to other regression functions.

Specifically-written method functions are defined for predict (standard predictions) and blup (best linear unbiased predictions). The method function simulate produces simulated outcomes from a fitted model, while qtest performs the Cochran Q test for heterogeneity. Other methods have been produced for summary, logLik, coef, and vcov.

Specific methods are also available for model.frame and model.matrix. In particular, the former produces the model frame (a data frame with special attributes storing the variables used for fitting) with the additional class "data.frame.mixmeta". A method terms is also available for extracting the terms object (only for fixed-effects or full). Methods na.omit and na.exclude for this class are useful for the handling of missing values in mixmeta objects.

Printing functions for the objects of classes defined above are also provided. anova methods for performing tests in mixmeta objects are in development.

All the methods above are visible (exported from the namespace) and documented. In additions, several default method functions for regression are also applicable to objects of class "mixmeta", such as fitted, residuals, AIC and BIC, drop1 and add1, or update, among others.

References

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].

See Also

See mixmeta. See lm or glm for standard regression functions. See mixmeta-package for an overview of this modelling framework.

Examples

Run this code
# NOT RUN {
# RUN THE MODEL
model <- mixmeta(cbind(PD,AL)~pubyear, S=berkey98[5:7], data=berkey98)

# INSPECT THE OBJECT
names(model)

# LABELS
model$lab

# FORMULA
model$formula

# CONVERGED?
model$converged
# }

Run the code above in your browser using DataLab