fitted glm model object.
This is assumed to be the result of some fit that produces
an object inheriting from the class "glm", in the sense that
the components returned by the glm() function will be available.
OPTIONAL ARGUMENTS:
dispersion:
a supplied value for the dispersion parameter.
The default is 1 for the binomial or poisson families.
For other families the default is the residual Chi-square statistic divided
by the residual degrees of freedom.
For the Gaussian family, for example, the dispersion parameter is
the error variance and the default is the Residual sum of
squares divided by the residual degrees of freedom.
Supplying a value of 0 causes the Chi-squared
estimate to be used in all cases.
correlation:
optional argument. If False, the correlation matrix for the coefficients
is not computed (useful for models with many coefficients).
VALUE:
a list is returned with the following components.
call,:
as contained on object
coefficients:
A matrix with three columns, containing the coefficients, their standard errors
and the corresponding t-statistic.
dispersion:
the dispersion parameter used in the computations (see dispersion argument).
df:
The number of degrees of freedom for the model and for residuals.
deviance.resid:
the deviance residuals, as produced by residuals(object).
cov.unscaled:
The unscaled covariance matrix; i.e, a matrix such that multiplying it
by the dispersion parameter, or estimate thereof, produces an estimated
(asymptotic) covariance matrix for the coefficients.
correlation:
The computed correlation matrix for the coefficients in the model.
nas:
a logical vector indicating which, if any, coefficients are missing.
DETAILS:
This function is a method for the generic function
summary
for class
"glm".
It can be invoked by calling
summary
for an object of the appropriate class, or directly by calling
summary.glm
regardless of the class of the object.