pval_quantile: Randomization test for quantiles of individual treatment...

In li-xinran/RIQITE: Randomization Inference for Quantiles of Individual Treatment Effects

Randomization test for quantiles of individual treatment effects

Description

Obtain the p-value for testing the null hypothesis H0: \tau_{(k)} \leq c, or H0: \tau_{(k)} \geq c, or H0: \tau_{(k)} = c, where \tau_{(k)} denotes individual treatment effect at rank k.

Usage

pval_quantile(
  Z,
  Y,
  k,
  c,
  alternative = "greater",
  method.list = list(name = "Stephenson", s = 10),
  score = NULL,
  stat.null = NULL,
  nperm = 10^6,
  Z.perm = NULL,
  switch = TRUE
)

Arguments

Z	An n dimensional treatment assignment vector.
Y	An n dimensional observed outcome vector.
k	An integer between 1 and n specifying which quantile of individual effect is of interest.
c	A numerical object specifying the threshold for the null hypothesis.
alternative	A character takes value "greater", "less" and "two.sided", indicating the alternative hypothesis.
method.list	A list specifies the choice of the rank sum test statistic. For example, list(name="Wilcoxon") means the Wilcoxon rank sum statistic, and list(name = "Stephenson", s = 10) means the Stephenson rank sum statistic with parameter s=10.
score	An n dimensional transformed ranks, i.e., (phi(1), phi(2), ..., phi(n)), where phi() denotes the rank transformation function.
stat.null	An vector whose empirical distribution approximates the randomization distribution of the rank sum statistic.
nperm	A positive integer representing the number of permutations for approximating the randomization distribution of the rank sum statistic.
Z.perm	A n \times nperm matrix that specifies the permutated assignments for approximating the null distribution of the test statistic.
switch	A logical object indicating whether performing treatment label switching to make the treated group have larger size.

Value

The p-value for testing the specified null hypothesis of interest.

li-xinran/RIQITE documentation built on July 1, 2023, 6:58 p.m.