Control Function for plotvgam()

Provides default values for many arguments available for plotvgam().

Usage

plotvgam.control(which.cf = NULL,
    xlim = NULL, ylim = NULL, llty = par()$lty, slty = "dashed",
    pcex = par()$cex, pch = par()$pch, pcol = par()$col,
    lcol = par()$col, rcol = par()$col, scol = par()$col,
    llwd = par()$lwd, slwd = par()$lwd, add.arg = FALSE,
    one.at.a.time = FALSE, .include.dots = TRUE, noxmean = FALSE,
    shade = FALSE, shcol = "gray80", main = "", ...)

Arguments

which.cf

Integer vector specifying which component functions are to be plotted (for each covariate). Must have values from the set {1,2,...,\(M\)}.

xlim

Range for the x-axis.

ylim

Range for the y-axis.

llty

Line type for the fitted functions (lines). Fed into par(lty).

slty

Line type for the standard error bands. Fed into par(lty).

pcex

Character expansion for the points (residuals). Fed into par(cex).

pch

Character used for the points (residuals). Same as par(pch).

pcol

Color of the points. Fed into par(col).

lcol

Color of the fitted functions (lines). Fed into par(col).

rcol

Color of the rug plot. Fed into par(col).

scol

Color of the standard error bands. Fed into par(col).

llwd

Line width of the fitted functions (lines). Fed into par(lwd).

slwd

Line width of the standard error bands. Fed into par(lwd).

add.arg

Logical. If TRUE then the plot will be added to an existing plot, otherwise a new plot will be made.

one.at.a.time

Logical. If TRUE then the plots are done one at a time, with the user having to hit the return key between the plots.

.include.dots

Not to be used by the user.

noxmean

Logical. If TRUE then the point at the mean of \(x\), which is added when standard errors are specified and it thinks the function is linear, is not added. One might use this argument if ylab is specified.

shade, shcol

shade is logical; if TRUE then the pointwise SE band is shaded gray by default. The colour can be adjusted by setting shcol. These arguments are ignored unless se = TRUE and overlay = FALSE; If shade = TRUE then scol is ignored.

main

Character vector, recycled to the number needed.

...

Other arguments that may be fed into par().

In the above, \(M\) is the number of linear/additive predictors.

Details

The most obvious features of plotvgam can be controlled by the above arguments.

Value

A list with values matching the arguments.

References

Yee, T. W. and Wild, C. J. (1996). Vector generalized additive models. Journal of the Royal Statistical Society, Series B, Methodological, 58, 481–493.

Author

Thomas W. Yee

Examples

plotvgam.control(lcol = c("red", "blue"), scol = "darkgreen", se = TRUE)
#> $se
#> [1] TRUE
#> 
#> $which.cf
#> NULL
#> 
#> $xlim
#> NULL
#> 
#> $ylim
#> NULL
#> 
#> $llty
#> [1] "solid"
#> 
#> $slty
#> [1] "dashed"
#> 
#> $pcex
#> [1] 1
#> 
#> $pch
#> [1] 1
#> 
#> $pcol
#> [1] "black"
#> 
#> $lcol
#> [1] "red"  "blue"
#> 
#> $rcol
#> [1] "black"
#> 
#> $scol
#> [1] "darkgreen"
#> 
#> $llwd
#> [1] 1
#> 
#> $slwd
#> [1] 1
#> 
#> $add.arg
#> [1] FALSE
#> 
#> $noxmean
#> [1] FALSE
#> 
#> $one.at.a.time
#> [1] FALSE
#> 
#> $main
#> [1] ""
#> 
#> $shade
#> [1] FALSE
#> 
#> $shcol
#> [1] "gray80"
#>