Extracts, summarizes, and prints components of an object returned by
gls_mult(). Mean-model methods use normal Wald inference. The model
argument selects the mean or dispersion parameter block for coef() and
vcov().
Usage
# S3 method for class 'gls_mult'
coef(object, model = c("mean", "dispersion"), ...)
# S3 method for class 'gls_mult'
vcov(object, model = c("mean", "dispersion"), ...)
# S3 method for class 'gls_mult'
confint(object, parm, level = object$confidence_level, ...)
# S3 method for class 'gls_mult'
tests(object, parm, alpha = object$alpha, ...)
# S3 method for class 'gls_mult'
nobs(object, ...)
# S3 method for class 'gls_mult'
fitted(object, ...)
# S3 method for class 'gls_mult'
residuals(object, ...)
# S3 method for class 'gls_mult'
logLik(object, ...)
# S3 method for class 'gls_mult'
print(x, ...)
# S3 method for class 'gls_mult'
summary(object, ...)
# S3 method for class 'summary_gls_mult'
print(x, ...)Arguments
- object, x
An object returned by
gls_mult(), or its summary.- model
Parameter block to extract:
"mean"or"dispersion".- ...
Unused. Passing arguments raises an error.
- parm
Optional mean-coefficient names or integer positions.
- level
Confidence level for mean-coefficient intervals.
- alpha
Significance level for mean-coefficient tests.
Value
coef() returns a named numeric vector; vcov() returns a covariance
matrix; confint() and tests() return tibbles; fitted() and
residuals() return named numeric vectors; nobs() returns the sample size;
and logLik() returns a logLik object for maximum likelihood fits.
summary() returns an object of class summary_gls_mult, including fitted
conditional-variance and standard-deviation summaries in squared response
and response units. Print methods return their input invisibly.