PLreg (version 0.4.1)

plot.PLreg: Diagnostic Plots for PLreg Objects

Description

This function provides plots for diagnostic analysis of power logit regression models.

Usage

# S3 method for PLreg
plot(x, which = 1:4, type = "standardized", pch = "+", las = 1, cex = 0.8, ...)

Value

plot method for PLreg objects returns 7 types of diagnostic plots.

Arguments

x

fitted model object of class "PLreg".

which

numeric specifying a subset of plots (numbers between 1 and 7). Default is which = 1:4.

type

character specifying the type of residuals, see residuals.PLreg. Default is type = "standardized".

pch, las, cex, ...

graphical parameters (see par)

Details

The plot method for PLreg objects provides 7 types of diagnostic plots in the following order.

Residuals vs indexes of obs.

An index plot of the residuals versus indexes of observations.

Case-weight perturbation

An index plot of local influence based on the case-weight perturbation scheme.

Generalized leverage

A dispersion diagram of the generalized leverage versus the predicted values.

Residuals vs linear predictor

A dispersion diagram of the residuals versus the linear predictors.

Normal probability plot

A normal probability plot of the residuals.

Predicted vs observed values

A dispersion diagram of the predicted values versus the observed values.

Residuals vs v(z) function

A dispersion diagram of the \(v(z)\) function versus the residuals. For some power logit models, the \(v(z)\) function may be interpreted as weights in the estimation process. If family = "NO", the \(v(z)\) function is constant.

The which argument can be used to select a subset of the implemented plots. Default is which = 1:4.

See Also

PLreg, residuals.PLreg, envelope, influence

Examples

data("Firm")

fitPL <- PLreg(firmcost ~ sizelog + indcost | sizelog + indcost, data = Firm,
              family = "SLASH", zeta = 2.13)
par(mfrow = c(3,3))
plot(fitPL, type = "standardized")
par(mfrow = c(1, 1))