In dmbwebb/qval: Calculates FDR-adjusted q-values

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

qval

If you test multiple hypotheses at once, then you risk getting false positives. One way of dealing with this problem is by adjusting the p-values of your results to account for the fact that you've run multiple hypotheses. This package takes a vector of p-values, and outputs a vector of ''q-values'', in the style of Anderson (2008). Rejecting q-values below a threshold, say alpha = 0.05, will control for the ''false-discovery rate'' (FDR). In other words, the probability that a given significant result is a false positive will then be equal to or less than 0.05.

Installation

You can install the development version from GitHub with:

# install.packages("devtools")
devtools::install_github("dmbwebb/qval")

Example

This is a basic example which shows you how to solve a common problem:

library(qval)
set.seed(12345)
pval_example <- c(runif(10, 0, 1), runif(2, 0, 0.05))
pval_example
q_val(pval_example)

dmbwebb/qval documentation built on Dec. 31, 2020, 11:21 p.m.