sd

0th

Percentile

Standard Deviation

This function computes the standard deviation of the values in x. If na.rm is TRUE then missing values are removed before computation proceeds.

Keywords
univar
Usage
sd(x, na.rm = FALSE)
Arguments
x

a numeric vector or an R object which is coercible to one by as.double(x).

na.rm

logical. Should missing values be removed?

Details

Like var this uses denominator \(n - 1\).

The standard deviation of a zero-length vector (after removal of NAs if na.rm = TRUE) is not defined and gives an error. The standard deviation of a length-one vector is NA.

See Also

var for its square, and mad, the most robust alternative.

Aliases
  • sd
Examples
library(stats) # NOT RUN { sd(1:2) ^ 2 # }
Documentation reproduced from package stats, version 3.5.1, License: Part of R 3.5.1

Community examples

richie@datacamp.com at Jan 17, 2017 stats v3.3.1

The standard deviation of random numbers should be close to (but not exactly) what you ask for. ```{r} x <- rnorm(1000, sd = 5) sd(x) ``` If there are any missing values, the standard deviation is also missing. ```{r} sd(c(1, 2, NA)) ``` You can exclude missing values by setting `na.rm = TRUE`. ```{r} sd(c(1, 2, NA), na.rm = TRUE) ``` If `x` has length 1 or 0, the result is `NA`. ```{r} sd(1) sd(numeric()) ```