| summary.gnm {gnm} | R Documentation |
summary method for objects of class "gnm"
## S3 method for class 'gnm':
summary(object, dispersion = NULL, correlation = FALSE,
symbolic.cor = FALSE, ...)
## S3 method for class 'summary.gnm':
print(x, digits = max(3, getOption("digits") - 3),
signif.stars = getOption("show.signif.stars"),
symbolic.cor = x$symbolic.cor, ...)
object |
an object of class "gnm". |
x |
an object of class "summary.gnm". |
dispersion |
the dispersion parameter for the fitting family. By
default it is obtained from object. |
correlation |
logical: if TRUE, the correlation matrix of
the estimated parameters is returned. |
digits |
the number of siginificant digits to use when printing. |
symbolic.cor |
logical: if TRUE, the correlations are
printed in a symbolic form rather than numbers (see
symnum). |
signif.stars |
logical. If TRUE, "significance stars" are
printed for each coefficient. |
... |
further arguments passed to or from other methods. |
print.summary.gnm prints the original call to gnm; a
summary of the deviance residuals from the model fit; the coefficients
of the model; the residual deviance; the Akaike's Information
Criterion value, and the number of main iterations performed.
Standard errors, z-values and p-values are printed alongside the
coefficients, with "significance stars" if signif.stars is
TRUE.
When the "summary.gnm" object has a "correlation"
component, the lower triangle of this matrix is also printed, to two
decimal places (or symbolically); to see the full matrix of
correlations print summary(object, correlation =
TRUE)$correlation directly.
The standard errors returned by summary.gnm are scaled by
sqrt(dispersion). If the dispersion is not specified, it is
taken as 1 for the binomial and Poisson families,
and otherwise estimated by the residual Chi-squared statistic divided
by the residual degrees of freedom. For coefficients that have been
constrained or are not estimable, the standard error is returned as
NA.
summary.gnm returns an object of class "summary.gnm",
which is a list with components
call |
the "call" component from object. |
eliminate |
the "eliminate" component from object. |
family |
the "family" component from object. |
deviance |
the "deviance" component from object. |
aic |
the "aic" component from object. |
df.residual |
the "df.residual" component from object. |
iter |
the "iter" component from object. |
deviance.resid |
the deviance residuals, see
residuals.glm. |
coefficients |
the matrix of coefficients, standard errors, z-values and p-values. |
dispersion |
either the supplied argument or the estimated dispersion if
the latter is NULL. |
df |
a 3-vector of the rank of the model; the number of residual degrees of freedom, and number of unconstrained coefficients. |
cov.scaled |
the estimated covariance matrix scaled by
dispersion (see vcov.gnm for more details). |
correlation |
(only if correlation is true) the
estimated correlations of the estimated coefficients. |
symbolic.cor |
(only if correlation is true) the value
of the argument symbolic.cor. |
The gnm class includes generalized linear models, and it
should be noted that summary.gnm differs from
summary.glm in that it does not omit coefficients which
are NA from the objects it returns. (Such coefficients are
NA since they have been fixed at 0 either by use of the
constrain argument to gnm or by a convention to handle
linear aliasing).
Heather Turner
## Following on from example(gnm)
data(cautres)
set.seed(1)
## Fit model as before
doubleUnidiff <- gnm(Freq ~ election:vote + election:class:religion +
Mult(Exp(election), religion:vote) +
Mult(Exp(election), class:vote), family = poisson,
data = cautres)
## Summarize results
summary(doubleUnidiff)