reStruct {nlme}  R Documentation 
Random Effects Structure
Description
This function is a constructor for the reStruct
class,
representing a random effects structure and consisting of a list of
pdMat
objects, plus a settings
attribute containing
information for the optimization algorithm used to fit the associated
mixedeffects model.
Usage
reStruct(object, pdClass, REML, data)
## S3 method for class 'reStruct'
print(x, sigma, reEstimates, verbose, ...)
Arguments
object 
any of the following: (i) a onesided formula of the form
~x1+...+xn  g1/.../gm , with x1+...+xn specifying the
model for the random effects and g1/.../gm the grouping
structure (m may be equal to 1, in which case no / is
required). The random effects formula will be repeated for all levels
of grouping, in the case of multiple levels of grouping; (ii) a list of
onesided formulas of the form ~x1+...+xn  g , with possibly
different random effects models for each grouping level. The order of
nesting will be assumed the same as the order of the elements in the
list; (iii) a onesided formula of the form ~x1+...+xn , or a
pdMat object with a formula (i.e. a nonNULL value for
formula(object) ), or a list of such formulas or pdMat
objects. In this case, the grouping structure formula will be derived
from the data used to to fit the mixedeffects model, which should
inherit from class groupedData ; (iv) a named list of formulas or
pdMat objects as in (iii), with the grouping factors as
names. The order of nesting will be assumed the same as the order of
the order of the elements in the list; (v) an reStruct object.

pdClass 
an optional character string with the name of the
pdMat class to be used for the formulas in
object . Defaults to "pdSymm" which corresponds to a
general positivedefinite matrix.

REML 
an optional logical value. If TRUE , the associated
mixedeffects model will be fitted using restricted maximum
likelihood; else, if FALSE , maximum likelihood will be
used. Defaults to FALSE .

data 
an optional data frame in which to evaluate the variables
used in the random effects formulas in object . It is used to
obtain the levels for factors , which affect the dimensions and
the row/column names of the underlying pdMat objects. If
NULL , no attempt is made to obtain information on
factors appearing in the formulas. Defaults to the
parent frame from which the function was called.

x 
an object inheriting from class reStruct to be printed.

sigma 
an optional numeric value used as a multiplier for
the squareroot factors of the pdMat components (usually the
estimated withingroup standard deviation from a mixedeffects
model). Defaults to 1.

reEstimates 
an optional list with the random effects estimates
for each level of grouping. Only used when verbose = TRUE .

verbose 
an optional logical value determining if the random
effects estimates should be printed. Defaults to FALSE .

... 
Optional arguments can be given to other methods for this
generic. None are used in this method.

Value
an object inheriting from class reStruct
, representing a random
effects structure.
Author(s)
JosÃ© Pinheiro and Douglas Bates bates@stat.wisc.edu
See Also
groupedData
,
lme
,
pdMat
,
solve.reStruct
,
summary.reStruct
,
update.reStruct
Examples
rs1 < reStruct(list(Dog = ~day, Side = ~1), data = Pixel)
rs1
[Package
nlme version 3.1120
Index]