plot.dfunc: plot.dfunc - Plot method for distance (detection) functions

Description

Plot method for objects of class 'dfunc'. Objects of class 'dfunc' are estimated distance functions produced by dfuncEstim.

Usage

# S3 method for dfunc
plot(x, ...)

Value

The input distance function is returned, with two additional components than can be used to reconstruct the plotted bars. (To obtain values of the plotted distance functions, use predict

with type = "distances".) The additional components are:

barHeights: A vector containing the scaled bar heights drawn on the plot.
barWidths: A vector or scalar of the bar widths drawn on the plot, with measurement units.

Re-plot the bars with barplot( return$barHeights, width = return$barWidths ).

Arguments

x

An estimated detection function object, normally produced by calling dfuncEstim.

...

Arguments passed on to plot.dfunc.para

include.zero: Boolean value specifying whether to include 0 on the x-axis of the plot. A value of TRUE will include 0 on the left hand end of the x-axis regardless of the range of distances. A value of FALSE will plot only the observation strip (w.lo to w.hi).

nbins

Internally, this function uses hist to compute histogram bars for the plot. This argument is the breaks argument to hist. This can be either a vector giving the breakpoints between bars, the suggested number of bars (a single number), a string naming an algorithm to compute the number of bars, or a function to compute the number of bars. See hist for all options.

newdata

Data frame (similar to newdata parameter of lm) containing new values for covariates in the distance function. One distance function is computed and plotted for each row in the data frame. If newdata is NULL, a single distance function is plotted for mean values of all numeric covariates and mode values for all factor covariates.

legend

Logical scalar for whether to include a legend. If TRUE, a legend will be included on the plot detailing the covariate values used to generate the plot.

plotBars

Logical scalar for whether to plot the histogram of distances behind the distance function. If FALSE, no histogram is plotted, only the distance function line(s).

xlab

Label for the x-axis

ylab

Label for the y-axis

density

If plotBars=TRUE, a vector giving the density of shading lines, in lines per inch, for the bars underneath the distance function, repeated as necessary to exceed the number of bars. Values of NULL or a number strictly less than 0 mean solid fill using colors from parameter col. If density = 0, bars are not filled and only the borders are rendered. If density > 0, bars are shaded with colors and angles from parameters col and angle.

angle

When density > 0, the slope of bar shading lines, given as an angle in degrees (counter-clockwise), repeated as necessary to exceed the number of bars.

col

A vector of bar fill colors or line colors when bars are drawn and density != 0, repeated as necessary to exceed the number of bars. Also used for the bar borders when border = TRUE.

border

The color of bar borders when bars are plotted, repeated as necessary to exceed the number of bars. A value of NA or FALSE means no borders. If bars are shaded with lines (i.e., density>0), border = TRUE uses the same color for the border as for the shading lines. Otherwise, fill color or shaded line color are specified in col while border color is specified in border.

vertLines

Logical scalar specifying whether to plot vertical lines at w.lo and w.hi from 0 to the distance function.

col.dfunc

Color of the distance function(s). If only one distance function (one line) is being plotted, the default color is "red". If covariates or newdata are present, the default value uses graphics::rainbow(n), where n is the number of plotted distance functions. Otherwise, col.dfunc is replicated to the required length. Plot all distance functions in the same color by setting col.dfunc to a scalar. Plot blue-red pairs of distance functions by setting col.dfunc = c("blue", "red"). Etc.

lty.dfunc

Line type of the distance function(s). If covariates or newdata is present, the default uses line types to 1:n, where n is the number of plotted distance functions. Otherwise, lty.dfunc is replicated to the required length. Plot solid lines by specifying lty.dfunc = 1. Plot solid-dashed line pairs by specifying lty.dfunc = c(1,2). Etc.

lwd.dfunc

Line width of the distance function(s), replicated to the required length. Default is 2 for all lines.

Details

If plotBars is TRUE, a scaled histogram is plotted and the estimated distance function is plotted over the top of it. When bars are plotted, this routine uses graphics::barplot for setting up the initial plotting region and most parameters to graphics::barplot can be specified (exceptions noted above in description of '...').

The form of the likelihood and any series expansions is printed in the main title (overwrite this with main="<my title>"). Convergence of the distance function is checked. If the distance function did not converge, a warning is printed over the top of the histogram. If one or more parameter estimates are at their limits (likely indicating non-convergence or poor fit), another warning is printed.

Examples

Run this code

set.seed(87654)
x <- rnorm(1000, mean=0, sd=20)
x <- x[x >= 0]
x <- units::set_units(x, "ft")
Df <- data.frame(transectID = "A"
               , distance = x
                ) |> 
  dplyr::nest_by( transectID
               , .key = "detections") |> 
  dplyr::mutate(length = units::set_units(1,"mi"))
attr(Df, "detectionColumn") <- "detections"
attr(Df, "obsType") <- "single"
attr(Df, "transType") <- "line"
attr(Df, "effortColumn") <- "length"
is.RdistDf(Df) # TRUE

dfunc <- Df |> dfuncEstim(distance ~ 1, likelihood="halfnorm")
plot(dfunc)
plot(dfunc, nbins=25)

# showing effects of plot params
plot(dfunc
  , col=c("red","blue","orange")
  , border="black"
  , xlab="Off-transect distance"
  , ylab="Prob"
  , vertLines = FALSE
  , main="Showing plot params")
 
plot(dfunc
   , col="purple"
   , density=30
   , angle=c(-45,0,45)
   , cex.axis=1.5
   , cex.lab=2
   , ylab="Probability") 

plot(dfunc
   , col=c("grey","lightgrey")
   , border=NA) 

plot(dfunc
   , col="grey"
   , border=0
   , col.dfunc="blue"
   , lty.dfunc=2
   , lwd.dfunc=4
   , vertLines=FALSE)

plot(dfunc
   , plotBars=FALSE
   , cex.axis=1.5
   , col.axis="blue")
rug(distances(dfunc))

# Plot showing f(0)
hist(distances(dfunc)
   , n = 40
   , border = NA
   , prob = TRUE)
x <- seq(dfunc$w.lo, dfunc$w.hi, length=200)
g <- predict(dfunc, type="dfunc", distances = x, newdata = data.frame(a=1))
f <- g[,1] / ESW(dfunc)[1]
# Check integration:
sum(diff(x)*(f[-1] + f[-length(f)]) / 2) # Trapazoid rule; should be 1.0
lines(x, f) # hence, 1/f(0) = ESW

# Covariates: detection by observer
data(sparrowDfuncObserver) # pre-estimated model

obsLevs <- levels(sparrowDfuncObserver$data$observer)
plot(sparrowDfuncObserver
   , newdata = data.frame(observer = obsLevs)
   , vertLines = FALSE
   , col.dfunc = heat.colors(length(obsLevs))
   , col = c("grey","lightgrey")
   , border=NA
   , main="Detection by observer")