Calculate Means Using the Pool Adjacent Violators Algorithm (PAVA)

This function computes adjusted means and standard errors for groups defined by a factor variable using the Pool Adjacent Violators Algorithm (PAVA).

Usage

pavaMean(x, g, alternative = "greater")

Arguments

x: A numeric vector of observations.
g: A factor variable that defines the groups for which to calculate means.
alternative: A character string specifying the alternative hypothesis. Options are "greater" (default) or "less".

Value

A data frame containing the following columns:

pavaMean: The adjusted means for each group.
SE.diff: The standard errors of the differences.

Examples

# Example usage:
x <- c(1, 2, 3, 4, 5, 6)
g <- factor(c("A", "A", "B", "B", "C", "C"))
result <- pavaMean(x, g)
print(result)
#>   pavaMean   SE.diff
#> A      1.5 0.7071068
#> B      3.5 0.7071068
#> C      5.5 0.7071068
x <- c(106, 114, 116, 127, 145,
       110, 125, 143, 148, 151,
       136, 139, 149, 160, 174)
g <- gl(3,5)
levels(g) <- c("0", "I", "II")
pavaMean(x,g)
#>    pavaMean SE.diff
#> 0     121.6 10.1712
#> I     135.4 10.1712
#> II    151.6 10.1712