MASS (version 7.3-36)

loglm1: Fit Log-Linear Models by Iterative Proportional Scaling -- Internal function

Description

loglm1 is an internal function used by loglm. It is a generic function dispatching on the data argument.

Usage

loglm1(formula, data, ...)
## S3 method for class 'xtabs':
loglm1(formula, data, \dots)
## S3 method for class 'data.frame':
loglm1(formula, data, \dots)
## S3 method for class 'default':
loglm1(formula, data, start = rep(1, length(data)), fitted = FALSE,
       keep.frequencies = fitted, param = TRUE, eps = 1/10,
       iter = 40, print = FALSE, ...)

Arguments

formula

A linear model formula specifying the log-linear model. See loglm for its interpretation.

data

Numeric array or data frame. In the first case it specifies the array of frequencies; in then second it provides the data frame from which the variables occurring in the formula are preferentially obtained in the usual way.

This argument

start, param, eps, iter, print

Arguments passed to loglin.

fitted

logical: should the fitted values be returned?

keep.frequencies

If TRUE specifies that the (possibly constructed) array of frequencies is to be retained as part of the fitted model object. The default action is to use the same value as that used for fitted.

...

arguments passed to the default method.

Value

• An object of class "loglm".

See Also

loglm, loglin