burden_test: Carry out a Fisher's exact test

In adamwaring/POSBURDEN: Rare variant association utilising burden and positional information.

Description

Burden test with formatting step to make a contingency table

Usage

burden_test(
  car = NULL,
  status = NULL,
  n1 = NULL,
  n2 = NULL,
  ss1 = NULL,
  ss2 = NULL,
  alternative = "greater"
)

Arguments

car	vector of carrier status. 0 for non-carriers. 1 for carriers.
status	vector of cohort status. 0 for controls. 1 for cases.
n1	number of carriers cases
n2	number of carriers controls
ss1	sample size cases
ss2	sample size controls
alternative	indicates the alternative hypothesis and must be one of "two.sided", "greater" or "less".

Details

Fisher.test from base R with extra formatting steps.

For a one-sided test i.e. excess in cases, use the default alternative="greater"

Use $p for p-value Use $est for odds-ratio Use $conf.int[1:2] for 95

Value

Returns an object of class htest - use $p for p-value

Author(s)

Adam Waring - [e-mail]

Examples

# For the simple case where you have the vector status (binary case or control) and a vector of whether they
have a variant 'car' (presumably after filtering) then;

N = 100
car = sample(c(0, 1), N, rep=T)
status = sample(c(0, 1), N, rep=T)

burden_test(car, status)

burden_test(n1=10, n2=20, ss1=100, ss2=100)

adamwaring/POSBURDEN documentation built on Feb. 21, 2020, 11:21 a.m.