weighted_mode: Weighted mode

In marberts/smart: Steve Martin's Assorted R Toolbox

Description

Calculate the weighted mode of a vector.

Usage

weighted_mode(x, w = rep(1, length(x)), na.rm = FALSE)

Arguments

x	An atomic vector.
w	A numeric vector of weights, the same length as x. The default gives each element of x equal weight.
na.rm	Should missing values in x and w be removed?

Details

Returns the value(s) in x with the largest weight, which by default is the most frequently occurring values in x. This is equivalent to choosing a value m that minimizes ∑ w[x != m].

The mode need not be unique, and a warning is given in this case.

Value

A vector of the same type as x that gives the mode(s).

Examples

# Unique mode
weighted_mode(c(1, 3, 2, 1))
weighted_mode(c(TRUE, FALSE, TRUE, FALSE), 1:4)

# Two modes
weighted_mode(c("a", "b", "c", "b", "c"))

# Notice that the mode is known despite the NA
weighted_mode(c(1, 1, 1, 2, NA))

# But this isn't always the case
weighted_mode(c(1, 1, 2, NA))

marberts/smart documentation built on March 9, 2021, 5:31 p.m.