nlme (version 3.1-38)

reStruct: 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 mixed-effects model.

Usage

reStruct(object, pdClass, REML, data)

Arguments

object

any of the following: (i) a one-sided 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

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 positive-definite matrix.

REML

an optional logical value. If TRUE, the associated mixed-effects 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

Value

• an object inheriting from class reStruct, representing a random effects structure.

See Also

pdMat, lme, groupedData

Examples

data(Pixel)
rs1 <- reStruct(list(Dog = ~day, Side = ~1), data = Pixel)
rs1