Print data objects and statistical model summaries in abbreviated form.

`brief(object, ...)`# S3 method for data.frame
brief(object, rows = if (nr <= 10)="" c(nr,="" 0)="" else="" c(3,="" 2),="" cols,="" head="FALSE," tail="FALSE," elided="TRUE," classes="inherits(object," "data.frame"),="" ...)="" #="" s3="" method="" for="" matrix="" brief(object,="" rows="if" (nr="" <="10)" ...)<="" p="">

# S3 method for numeric
brief(object, rows = c(2, 1), elided = TRUE, ...)
# S3 method for integer
brief(object, rows = c(2, 1), elided = TRUE, ...)
# S3 method for character
brief(object, rows = c(2, 1), elided = TRUE, ...)
# S3 method for factor
brief(object, rows=c(2, 1), elided=TRUE, ...)

# S3 method for list
brief(object, rows = c(2, 1), elided = TRUE, ...)

# S3 method for function
brief(object, rows = c(5, 3), elided = TRUE, ...)

# S3 method for lm
brief(object, terms = ~ .,
intercept=missing(terms), pvalues=FALSE,
digits=3, horizontal=TRUE, vcov., ...)

# S3 method for glm
brief(object, terms = ~ .,
intercept=missing(terms), pvalues=FALSE,
digits=3, horizontal=TRUE, vcov., dispersion, exponentiate, ...)

# S3 method for multinom
brief(object, terms = ~ .,
intercept=missing(terms), pvalues=FALSE,
digits=3, horizontal=TRUE, exponentiate=TRUE, ...)

# S3 method for polr
brief(object, terms = ~ .,
intercept, pvalues=FALSE,
digits=3, horizontal=TRUE, exponentiate=TRUE, ...)

# S3 method for default
brief(object, terms = ~ .,
intercept=missing(terms), pvalues=FALSE,
digits=3, horizontal=TRUE, ...)

object

a data or model object to abbreviate.

rows

for a matrix or data frame, a 2-element integer vector with the number of rows to print at the beginning and end of the display; for a vector or factor, the number of lines of output to show at the beginning and end; for a list, the number of elements to show at the beginning and end; for a function, the number of lines to show at the beginning and end.

cols

for a matrix or data frame, a 2-element integer vector with the number of columns to print at the beginning (i.e., left) and end (right) of the display.

head, tail

alternatives to the `rows`

argument; if `TRUE`

, print the first or last 6
rows; can also be the number of the first or last few rows to print; only one of `heads`

and
`tails`

should be specified; ignored if `FALSE`

(the default).

elided

controls whether to report the number of elided elements, rows, or columns; default is `TRUE`

.

classes

show the class of each column of a data frame at the top of the column; the classes are
shown in single-character abbreviated form---e.g., `[f]`

for a factor, `[i]`

for an integer
variable, `[n]`

for a numeric variable, `[c]`

for a character variable.

terms

a one-sided formula giving the terms to summarize; the default is `~ .`

---i.e., to summarize all terms in the model.

intercept

whether or not to include the intercept; the default is `TRUE`

unless the `terms`

argument is given, in which
case the default is `FALSE`

; ignored for `polr`

models.

pvalues

include the p-value for each coefficient in the table; default is `FALSE`

.

exponentiate

for a `"glm"`

or `"glmerMod"`

model using the `log`

or `logit`

link, or a
`"polr"`

or `"multinom"`

model, show exponentiated coefficient estimates and confidence bounds.

digits

significant digits for printing.

horizontal

if `TRUE`

(the default), orient the summary produced by `brief`

horizontally, which typically saves space.

dispersion

see `summary.glm`

vcov.

either a matrix giving the estimated covariance matrix of the estimates,
or a function that
when called with `object`

as an argument returns an estimated covariance matrix
of the estimates. The default `vcov. = vcov(object, complete=FALSE)`

uses the
usual estimated covariance matrix with NA for any row and column with aliased regressors.
Other choices include the functions documented at `hccm`

, and a bootstrap
estimate `vcov.=vcov(Boot(object))`

; see the documentation for `Boot`

.
For the `glm`

method, if the `vcov.`

or `dispersion`

argument is specified,
then Wald-based confidence limits are computed; otherwise the reported confidence limits
are computed by profiling the likelihood.
NOTES: (1) The `dispersion`

and `vcov.`

arguments may not *both* be
specified. (2) Setting `vcov.=vcov`

returns an error if the model includes aliased
terms; use `vcov.=vcov(object, complete=FALSE)`

. (3) The `hccm`

method will
generally return a matrix of full rank even if the model has aliased terms. Similarly
`vcov.=vcov(Boot(object))`

may return a full rank matrix, or it will a matrix with
NA corresponding to aliased regressors if same regressors are aliased in every bootstrap
sample.

…

arguments to pass down.

Invisibly returns `object`

for a data object, or summary for a model object.

Fox, J. and Weisberg, S. (2019)
*An R Companion to Applied Regression*, Third Edition, Sage.

# NOT RUN { brief(rnorm(100)) brief(Duncan) brief(OBrienKaiser, elided=TRUE) brief(matrix(1:500, 10, 50)) brief(lm) mod.prestige <- lm(prestige ~ education + income + type, Prestige) brief(mod.prestige, pvalues=TRUE) brief(mod.prestige, ~ type) mod.mroz <- glm(lfp ~ ., data=Mroz, family=binomial) brief(mod.mroz) # }