plot.lcc: Diagnostic Plots for an `lcc` Object

Description

Generates a series of diagnostic plots for evaluating the fit of a linear mixed-effects model represented by an lcc object. This function provides six types of plots, including residual plots, fitted value comparisons, and normal Q-Q plots. Users can select specific plots or display all by default.

Usage

# S3 method for lcc
plot(x, which = c(1L:6L),
     caption = list("Residuals vs Fitted",
                    "Residuals vs Time",
                    "Residuals by Subject",
                    "Observed values vs Fitted values",
                    "Normal Q-Q Plot (Conditional residuals)",
                    "Normal Q-Q Plot (Random effects)"),
     sub.caption = NULL, main = NULL,
     panel = if(add.smooth) panel.smooth else points,
     add.smooth = TRUE, ask = TRUE,
     id.n = 3, labels.id = names(residuals(x)),
     label.pos = c(4, 2), cex.id = 0.75, cex.caption = 1,
     cex.oma.man = 1.25, ...)

Arguments

x: An object of class lcc, representing a fitted longitudinal concordance correlation function.
which: A numeric vector specifying which plots to display. The valid range is c(1L:6L), corresponding to the plot types.
caption: Captions for the plots, provided as a vector or list of valid graphics annotations. Default captions are provided for each plot.
sub.caption: A common sub-title for all plots; defaults to NULL.
main: The main title for the plots, displayed above the captions.
panel: Panel function to be used for adding points to the plots. Defaults to panel.smooth if add.smooth is TRUE, otherwise points.
add.smooth: Logical; indicates whether a smoother should be added to most plots. Defaults to TRUE.
ask: Logical; if TRUE, prompts the user before displaying each plot in a multi-plot layout. Defaults to TRUE.
id.n: Number of extreme points to label in the first three plots.
labels.id: Labels for the extreme points, defaulting to observation numbers if NULL.
label.pos: Positioning of labels in the left and right halves of the graph, applicable for plots 1-3.
cex.id: Magnification factor for point labels.
cex.caption: Size of the plot captions.
cex.oma.man: Size of the overall margin annotation (applies only if sub.caption is above the figures in multi-plot layouts).
...: Additional graphical parameters passed to par.

Author

Thiago de Paula Oliveira, thiago.paula.oliveira@alumni.usp.br

Details

The Q-Q plots use normalized residuals. Standardized residuals are pre-multiplied by the inverse square-root factor of the estimated error correlation matrix, while random effects are adjusted using the estimated variances from matrix G. Simulation envelopes in Q-Q plots are generated using the hnp package.

The function is partly adapted from plot.lm.

Examples

Run this code

if (FALSE) {
fm1 <- lcc(data = hue, subject = "Fruit", resp = "H_mean",
           method = "Method", time = "Time", qf = 2, qr = 2)
plot(fm1)
}