plot_2d {adaptMT}

Plotting Functions for AdaPT with 2D Covariates

Description

Plotting the outputs of adapt when x is 2-dimensional, including threshold curves and level curves of local FDR.

Usage

plot_2d_thresh(obj, x, pvals, alpha, title, xlab = NULL, ylab = NULL,
  keyaxes = list(), ...)

plot_2d_lfdr(obj, x, pvals, alpha, title, targetp, xlab = NULL, ylab = NULL,
  keyaxes = list(), ...)

Arguments

obj

an 'adapt' object

x

covariates (i.e. side-information). Should be compatible to models and 2-dimensional.

pvals

a vector of values in [0, 1]. P-values

alpha

a positive scalar in (0, 1). Target FDR level

title

a string. Title of the figure

xlab, ylab

a string. Label of x/y-axis

keyaxes

a list of arguments passed into axis. The graphical setting for the legend bar. An empty list by default

...

other arguments passed to par

targetp

a real in (0, 1). See Details

Details

The breaks in the legend of plot_2d_thresh correspond to the maximum, the 95

plot_2d_lfdr gives the contour plot of local FDR estimates when all p-values are equal to targetp. It is recommended to run plot_2d_lfdr for multiple targetp's ranging from 0.001, 0.005, 0.01, 0.05.

Examples

# Generate a 2-dim x
n <- 400
x1 <- x2 <- seq(-100, 100, length.out = 20)
x <- expand.grid(x1, x2)
colnames(x) <- c("x1", "x2")

# Generate p-values (one-sided z test)
# Set all hypotheses in the central circle with radius 30 to be
# non-nulls. For non-nulls, z~N(2,1) and for nulls, z~N(0,1).
H0 <- apply(x, 1, function(coord){sum(coord^2) < 900})
mu <- ifelse(H0, 2, 0)
set.seed(0)
zvals <- rnorm(n) + mu
pvals <- 1 - pnorm(zvals)

# Run adapt_gam with a 2d spline basis
library("mgcv")
formula <- "s(x1, x2)"
dist <- beta_family()
res <- adapt_gam(x = x, pvals = pvals, pi_formulas = formula,
                 mu_formulas = formula, dist = dist, nfits = 5)

# Plots
plot_2d_thresh(res, x, pvals, 0.3, "P-value Thresholds (alpha = 0.3)")
plot_2d_lfdr(res, x, pvals, 0.3, "Local FDR Estimates (alpha = 0.3, p = 0.01)", 0.01)