permutest (version 1.0.0)

npc: Run NPC

Description

This function takes a data frame and group and outcome column names as input and returns the nonparametric combination of tests (NPC) omnibus p-value

Usage

npc(
  df,
  group_col,
  outcome_cols,
  strata_col = NULL,
  test_stat = "diff_in_means",
  perm_func = permute_group,
  combn = "fisher",
  shift = 0,
  reps = 10000,
  perm_set = NULL,
  complete_enum = FALSE,
  seed = NULL
)

Value

The omnibus p-value

Arguments

df

A data frame

group_col

The name of the column in df that corresponds to the group label

outcome_cols

The names of the columns in df that corresponds to the outcome variable

strata_col

The name of the column in df that corresponds to the strata

test_stat

Test statistic function

perm_func

Function to permute group, default is permute_group which randomly permutes group assignment

combn

Combining function method to use, takes values 'fisher', 'tippett', or 'liptak', or a user defined function

shift

Value of shift to apply in one- or two-sample problem

reps

Number of iterations to use when calculating permutation p-value

perm_set

Matrix of permutations to use instead of reps iterations of perm_func

complete_enum

Boolean, whether to calculate P-value under complete enumeration of permutations

seed

An integer seed value

Examples

data <- data.frame(group = c(rep(1, 4), rep(2, 4)),
out1 = c(0, 1, 0, 0, 1, 1, 1, 0),
out2 = rep(1, 8))
output <- npc(df = data, group_col = "group",
              outcome_cols = c("out1", "out2"), perm_func = permute_group,
              combn = "fisher", reps = 10^4, seed=42)