FENmlm (version 2.4.4)

fitted.femlm: Extracts fitted values from a femlm fit

Description

This function extracts the fitted values from a model estimated with femlm. The fitted values that are returned are the expected predictor.

Usage

# S3 method for femlm
fitted(object, type = c("response", "link"), ...)
# S3 method for values.femlm
fitted(object, type = c("response", "link"), ...)

Value

It returns a numeric vector of length the number of observations used to estimate the model.

If type = "response", the value returned is the expected predictor, i.e. the expected value of the dependent variable for the fitted model: \(E(Y|X)\). If type = "link", the value returned is the linear predictor of the fitted model, that is \(X\cdot \beta\) (remind that \(E(Y|X) = f(X\cdot \beta)\)).

Arguments

object

An object of class femlm. Typically the result of a femlm estimation.

type

Character either equal to "response" (default) or "link". If type="response", then the output is at the level of the response variable, i.e. it is the expected predictor \(E(Y|X)\). If "link", then the output is at the level of the explanatory variables, i.e. the linear predictor \(X\cdot \beta\).

...

Not currently used.

Author

Laurent Berge

Details

This function returns the expected predictor of a femlm fit. The likelihood functions are detailed in femlm help page.

See Also

femlm, resid.femlm, predict.femlm, summary.femlm, vcov.femlm, getFE.

Examples

# simple estimation on iris data, clustering by "Species"
res_poisson = femlm(Sepal.Length ~ Sepal.Width + Petal.Length +
                    Petal.Width | Species, iris)

# we extract the fitted values
y_fitted_poisson = fitted(res_poisson)

# Same estimation but in OLS (Gaussian family)
res_gaussian = femlm(Sepal.Length ~ Sepal.Width + Petal.Length +
                    Petal.Width | Species, iris, family = "gaussian")

y_fitted_gaussian = fitted(res_gaussian)

# comparison of the fit for the two families
plot(iris$Sepal.Length, y_fitted_poisson)
points(iris$Sepal.Length, y_fitted_gaussian, col = 2, pch = 2)