Compute marginal effects (internal function)
get_dydx_continuous(model, ...)# S3 method for default
get_dydx_continuous(
model,
variable,
fitfram = insight::get_data(model),
group_name = NULL,
type = "response",
numDeriv_method = "simple",
...
)
Model object
Additional arguments are pushed forward to predict().
A string to identify the variable whose marginal effect to compute.
A data.frame over which to compute marginal effects.
String to identify the "group" or "level" of the terms to estimate. Groups are often used in models like multinomial logit where each level of the response variable is associated to its own set of coefficients.
Type(s) of prediction as string or vector This can differ based on the model type, but will typically be a string such as: "response", "link", "probs", or "zero".
Numeric vector of marginal effects associated to a continuous regressor