FDRCurve: FDR Curve

Description

Estimates the expected proportion of misclassified units when using a given r-value threshold. If plot=TRUE, the curve is plotted before the estimated function is returned.

Usage

FDRCurve(object, q, threshold = 1, plot = TRUE, xlim, ylim, xlab, ylab, main, ...)

Arguments

object

An object of class "rvals"

A value in between 0 and 1; the desired level of FDR control.

threshold

The r-value threshold.

plot

logical; if TRUE, the estimated FDR curve is plotted.

xlim,ylim

x and y - axis limits for the plot

xlab,ylab

x and y - axis labels

main

the title of the plot

…

additional arguments to plot.default

Value

A list with the following two components

fdrcurve

A function which returns the estimated FDR for each r-value threshold.

Rval.cut

The largest r-value cutoff which still gives an estimated FDR less than q.

Details

Consider parameters of interest $(\theta_1,...,\theta_n)$ with an effect of size of interest $\tau$. That is, a unit is taken to be "null" if $\theta_i \le \tau$ and taken to be "non-null" if $\theta_i > \tau$.

For r-values $r_1,...,r_n$ and a procedure which "rejects" units satisfying $r_i \le c$, the FDR is defined to be $$FDR(c) = P(\theta_i < \tau,r_i \le c)/P(r_i \le c).$$ FDRCurve estimates $FDR(c)$ for values of $c$ across (0,1) and plots (if plot=TRUE) the resulting curve.

Examples

Run this code

# NOT RUN {
n <- 500
theta <- rnorm(n)
ses <- sqrt(rgamma(n,shape=1,scale=1))
XX <- theta + ses*rnorm(n)
dd <- cbind(XX,ses)

rvs <- rvalues(dd, family = gaussian)

FDRCurve(rvs, q = .1, threshold = .3, cex.main = 1.5)
# }