wkdeplot: Plot a weighted kernel density estimate

In DeconWK: Deconvolution by Weighted Kernels

Description

Function to plot a weighted kernel density estimate.

Usage

wkde.plot(y, eval, sigma, h, w, gamma, method = "exact",
          RUG = TRUE, COMPARE = TRUE,
          XLAB = expression(italic(x)), YLAB = "density",
          COL = 1:2, LTY = rep(1, 2), LWD = rep(1, 2), YLIM = NULL)

Arguments

y	the observed, contaminated data.
eval	grid on which the deconvolution density estimate be calculated.
sigma	the standard deviation of the contaminating (normal) distribution.
h	the bandwidth to be used for the weighted kernel density estimate
w	the weights to be used.
gamma	the regularisation parameter to be used; either a scalar for methods "exact" and "svm", or a vector of values from which a suitable value is selected via K-fold cross-validation for methods "exact.cv" and "svm.cv"

.

method	method to be used to solve the quadratic programming problem involved in calculating the weights; if "exact" or "exact.cv" then solveqp is used, otherwise ipop from the kernlab package is used.
RUG	logical; if TRUE a rug is added to the plot indicating the location of the observed value and the weight attached to each observation.
COMPARE	logical; if TRUE a kernel density estimate with all weights equal to one is added to the plot.
XLAB	label for the x axis.
YLAB	label for the y axis.
COL	colours in which the density estimates should be drawn.
LTY	line type in which the density estimates should be drawn.
LWD	line width with which the density estimates should be drawn.
YLIM	limits for the y axis.

Details

If "eval" is not specified, it defaults to seq(min(y)-0.1*sd(y), max(y)+0.1*sd(y), length=100).

If "w" is not specified, it defaults to w.hat(y, sigma=sigma, h=h, gamma=gamma, METHOD=method).

If "h" is not specified, it defaults to bw.SJ(y, method="dpi").

Value

Invisible NULL. This function is called for its side effect of creating a plot.

Author(s)

Martin L Hazelton [e-mail]

Berwin A Turlach [e-mail]

References

Hazelton, M.L. and Turlach, B.A. (2009). Nonparametric density deconvolution by weighted kernel estimators, Statistics and Computing 19(3): 217–228. http://dx.doi.org/10.1007/s11222-008-9086-7.

See Also

wkde, w.hat

Examples

  set.seed(100719)
  sig <- sqrt(29/40)  # Var(Z)/Var(X) = 0.1
  y <- rden(100, DEN=3, sigma=sig)
  wkde.plot(y, sigma=sig, gamma=2.05)
  wkde.plot(y, sigma=sig, gamma=4.4)

DeconWK documentation built on May 2, 2019, 6:08 p.m.