Fitted Values of Selection Models
Calculate fitted values of sample selection models
## S3 method for class 'selection' fitted(object, part = "outcome", ... )
object |
object of class |
part |
character string indication which fitted values to extract: "outcome" for the fitted values of the outcome equation(s) or "selection" for the fitted values of the selection equation. |
... |
further arguments passed to other methods
(e.g. |
If the model was estimated by the 2-step method,
the fitted values of the outcome equation are calculated
using all regressors of this equation
including the inverse Mill's ratios,
i.e. the fitted values correspond to the conditional expectations
(see predict.selection
).
If the model was estimated by the maximum likelihood method,
the fitted values of the outcome equation are calculated
by disregarding the selection equation,
i.e. the fitted values correspond to the unconditional expectations
(see predict.selection
).
The fitted values of the selection equation are probabilities. If the dependent variable of the outcome equation is binary, also the fitted values of the outcome equation are probabilities.
A numeric vector of the fitted values.
Arne Henningsen
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.