[ME] estat wcorrelation -- Display within-cluster correlations and standard
deviations
Syntax
estat wcorrelation [, options]
options Description
-------------------------------------------------------------------------
at(at_spec) specify the cluster for which you want the
correlation matrix; default is the first two-level
cluster encountered in the data
all display correlation matrix for all the data
covariance display the covariance matrix instead of the
correlation matrix
list list the data corresponding to the correlation matrix
nosort list the rows and columns of the correlation matrix
in the order they were originally present in the
data
iterate(#) maximum number of iterations to compute random
effects; default is iterate(50); only for use after
menl
tolerance(#) convergence tolerance when computing random effects;
default is tolerance(1e-4); only for use after menl
format(%fmt) set the display format; default is format(%6.3f)
matlist_options style and formatting options that control how
matrices are displayed
-------------------------------------------------------------------------
Menu for estat
Statistics > Postestimation
Description
estat wcorrelation is for use after estimation with menl and mixed.
estat wcorrelation displays the overall correlation matrix for a given
cluster calculated on the basis of the design of the random effects and
their assumed covariance and the correlation structure of the residuals.
This allows for a comparison of different multilevel models in terms of
the ultimate within-cluster correlation matrix that each model implies.
Options
at(at_spec) specifies the cluster of observations for which you want the
within-cluster correlation matrix. at_spec is
relevel_var = value [relevel_var = value ...]
For example, if you specify
. estat wcorrelation, at(school = 33)
you get the within-cluster correlation matrix for those observations
in school 33. If you specify
. estat wcorrelation, at(school = 33 classroom = 4)
you get the correlation matrix for classroom 4 in school 33.
If at() is not specified, then you get the correlations for the first
level-two cluster encountered in the data. This is usually what you
want.
all specifies that you want the correlation matrix for all the data.
This is not recommended unless you have a relatively small dataset or
you enjoy seeing large n x n matrices. However, this can prove
useful in some cases.
covariance specifies that the within-cluster covariance matrix be
displayed instead of the default correlations and standard
deviations.
list lists the model data for those observations depicted in the
displayed correlation matrix. With linear mixed-effects models, this
option is also useful if you have many random-effects design
variables and you wish to see the represented values of these design
variables.
nosort lists the rows and columns of the correlation matrix in the order
that they were originally present in the data. Normally, estat
wcorrelation will first sort the data according to level variables,
by-group variables, and time variables to produce correlation
matrices whose rows and columns follow a natural ordering. nosort
suppresses this.
iterate(#) specifies the maximum number of iterations when computing
estimates of the random effects. The default is iterate(50). This
option is only for use after menl.
tolerance(#) specifies a convergence tolerance when computing estimates
of the random effects. The default is tolerance(1e-4). This option
is only for use after menl.
format(%fmt) sets the display format for the standard-deviation vector
and correlation matrix. The default is format(%6.3f).
matlist_options are style and formatting options that control how the
matrix (or matrices) is displayed; see [P] matlist for a list of
options that are available.
Examples
---------------------------------------------------------------------------
Setup
. webuse pig
. mixed weight week || id: week, covariance(unstructured)
Random-effects correlation matrix for level ID
. estat recovariance, correlation
Display within-cluster marginal standard deviations and correlations for
a cluster
. estat wcorrelation, format(%4.2g)
---------------------------------------------------------------------------
Setup
. webuse childweight
. mixed weight age || id: age, covariance(unstructured)
Display within-cluster correlations for the first cluster
. estat wcorrelation, list
Display within-cluster correlations for ID 258
. estat wcorrelation, at(id=258) list
---------------------------------------------------------------------------
Stored results
estat wcorrelation stores the following in r():
Matrices
r(sd) standard deviations
r(Corr) within-cluster correlation matrix
r(Cov) within-cluster variance-covariance matrix
r(G) variance-covariance matrix of random effects
r(Z) model-based design matrix
r(R) variance-covariance matrix of level-one errors
Results r(G), r(Z), and r(R) are available only after mixed.