Fits multinomial log-linear models via neural networks.
multinom(formula, data, weights, subset, na.action,
contrasts = NULL, Hess = FALSE, summ = 0, censored = FALSE,
model = FALSE, ...)
A nnet
object with additional components:
the residual deviance, compared to the full saturated model (that explains individual observations exactly). Also, minus twice log-likelihood.
the (effective) number of degrees of freedom used by the model
the AIC for this fit.
(if Hess
is true).
(if model
is true).
a formula expression as for regression models, of the form
response ~ predictors
. The response should be a factor or a
matrix with K columns, which will be interpreted as counts for each of
K classes.
A log-linear model is fitted, with coefficients zero for the first
class. An offset can be included: it should be a numeric matrix with K columns
if the response is either a matrix with K columns or a factor with K >= 2
classes, or a numeric vector for a response factor with 2 levels.
See the documentation of formula()
for other details.
an optional data frame in which to interpret the variables occurring
in formula
.
optional case weights in fitting.
expression saying which subset of the rows of the data should be used in the fit. All observations are included by default.
a function to filter missing data.
a list of contrasts to be used for some or all of the factors appearing as variables in the model formula.
logical for whether the Hessian (the observed/expected information matrix) should be returned.
integer; if non-zero summarize by deleting duplicate rows and adjust weights.
Methods 1 and 2 differ in speed (2 uses C
); method 3 also combines rows
with the same X and different Y, which changes the baseline for the
deviance.
If Y is a matrix with K
columns, interpret the entries as one
for possible classes, zero for impossible classes, rather than as
counts.
logical. If true, the model frame is saved as component model
of the returned object.
additional arguments for nnet
multinom
calls nnet
. The variables on the rhs of
the formula should be roughly scaled to [0,1] or the fit will be slow
or may not converge at all.
Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.
nnet
oc <- options(contrasts = c("contr.treatment", "contr.poly"))
library(MASS)
example(birthwt)
(bwt.mu <- multinom(low ~ ., bwt))
options(oc)
Run the code above in your browser using DataLab