summary.lm
Summary Method for Linear Models
Description
Summarize a fitted linear model.
Usage
## S3 method for class 'lm':
summary(object, correlation = FALSE, symbolic.cor = FALSE, ...)
## S3 method for class 'mlm':
summary(object, correlation = FALSE, symbolic.cor = FALSE, ...)
## S3 method for class 'summary.lm':
print(x, digits = max(3, getOption("digits") - 3), symbolic.cor = x$symbolic.cor, signif.stars = getOption("show.signif.stars", default = TRUE), ...)
Arguments
object |
a fitted linear model inheriting from class lm or mlm;
typically the output of the lm function when the
response is a vector or a matrix, respectively.
|
correlation |
a logical flag. If TRUE,
the correlation matrix for the coefficients is included in the summary. The default is FALSE.
|
symbolic.cor |
a logical flag. In summary.lm, if correlation is TRUE, symbolic.cor is included in the summary, and its value is the same as this argument. The default is FALSE.
|
x |
an object of class summary.lm resembling the output of the summary.lm function.
|
signif.stars |
a logical flat. If TRUE (the default), when you print the coefficient, "significance stars" are printed.
|
digits |
an integer used in print to indicate the number of significant digits to use when printing.
|
... |
extra arguments passed to or from other methods. The summary methods here
ignore these arguments and the print methods pass them onto lower level
printing routines.
|
Details
- summary.lm produces a summary object of class summary.lm.
- print.summary.lm prints such an object.
- summary.mlm produces a list of class listof containing
one summary.lm object for each column in the response matrix.
Value
summary.lm returns a list of class summary.lm
whose components call and terms are copied
from its object argument and whose other components are as follows.
residuals |
the residuals for the model.
These are the weighted residuals if weights were given in the model.
|
coefficients |
a matrix with one row for each coefficient in the fitted model.
The first column, "Estimate", gives the estimate of the coefficent, and the
others give the standard error ("Std. Error"), t value ("t value"), and
p value ("Pr(>|t|)") of the estimate.
|
aliased |
a logical vector to show if the original coefficients are aliased.
|
sigma |
the residual standard error estimate.
|
df |
a numeric vector of length three giving the rank of the model matrix,
the residual degrees of freedom, and the number of coefficients for the model.
|
fstatistic |
a numeric vector of length three giving the F-test for the regression.
The first element in the vector is the statistic,
and the last two elements are the degrees of freedom.
|
r.squared |
the multiple R-squared statistic for the model.
|
adj.r.squared |
the adjusted multiple R-squared statistic for the model.
|
cov.unscaled |
the unscaled covariance matrix.
Multiplying cov.unscaled by an estimate
of the error variance produces an estimated covariance matrix
for the coefficients.
|
correlation |
the computed correlation matrix for the coefficients in the model.
This is returned only if correlation=TRUE was set.
|
symbolic.cor |
this item appears only when correlation is true. Its value is the value of the argument symbolic.cor.
|
See Also
Examples
fit <- lm(ozone ~ radiation + temperature + wind, data=Sdatasets::air)
summary(fit)