plot.mfdr: Plot marginal false discovery rate curves

Description

Plot marginal false discovery rate curves from an mfdr or perm.ncvreg object.

Usage

# S3 method for mfdr
plot(
  x,
  type = c("mFDR", "EF"),
  log.l = FALSE,
  selected = TRUE,
  legend = TRUE,
  ...
)

Arguments

x: A perm.ncvreg or mfdr object.
type: What to plot on the vertical axis. mFDR plots the marginal false discovery rate; EF plots the expected number of false discoveries along with the actual number of variables included in the model.
log.l: Should horizontal axis be on the log scale? Default is FALSE.
selected: If TRUE (the default), places an axis on top of the plot denoting the number of variables in the model (i.e., that have a nonzero regression coefficient) at that value of lambda.
legend: For type="EF" plots, draw a legend to indicate which line is for the actual selections and which line is for the expected number of false discoveries? Default is TRUE.
...: Other graphical parameters to pass to plot()

Author

Patrick Breheny

References

Breheny P (2019). Marginal false discovery rates for penalized regression models. Biostatistics, 20: 299-314.

Examples

Run this code

data(Prostate)
fit <- ncvreg(Prostate$X, Prostate$y)

obj <- mfdr(fit)
obj[1:10,]

# Some plotting options
plot(obj)
plot(obj, type="EF")
plot(obj, log=TRUE)


# Comparison with perm.ncvreg
op <- par(mfrow=c(2,2))
plot(obj)
plot(obj, type="EF")
pmfit <- perm.ncvreg(Prostate$X, Prostate$y)
plot(pmfit)
plot(pmfit, type="EF")
par(op)