Returns the values the response variable(s) from a model object. If the model is a multivariate response model, a data frame with values from all response variables is returned.

Usage

get_response(
x,
select = NULL,
as_proportion = TRUE,
source = "environment",
verbose = TRUE
)

Arguments

x

A fitted model.

select

Optional name(s) of response variables for which to extract values. Can be used in case of regression models with multiple response variables.

as_proportion

Logical, if TRUE and the response value is a proportion (e.g. y1 / y2), then the returned response value will be a vector with the result of this proportion. Else, always a data frame is returned.

source

String, indicating from where data should be recovered. If source = "environment" (default), data is recovered from the environment (e.g. if the data is in the workspace). This option is usually the fastest way of getting data and ensures that the original variables used for model fitting are returned. Note that always the current data is recovered from the environment. Hence, if the data was modified after model fitting (e.g., variables were recoded or rows filtered), the returned data may no longer equal the model data. If source = "frame" (or "mf"), the data is taken from the model frame. Any transformed variables are back-transformed, if possible. This option returns the data even if it is not available in the environment, however, in certain edge cases back-transforming to the original data may fail. If source = "environment" fails to recover the data, it tries to extract the data from the model frame; if source = "frame" and data cannot be extracted from the model frame, data will be recovered from the environment. Both ways only returns observations that have no missing data in the variables used for model fitting.

verbose

Toggle warnings.

Value

The values of the response variable, as vector, or a data frame if x has more than one defined response variable.

Examples

if (require("lme4")) {
data(cbpp)
cbpp$trials <- cbpp$size - cbpp\$incidence
dat <<- cbpp

m <- glm(cbind(incidence, trials) ~ period, data = dat, family = binomial)