R: Weighted variance and weighted standard deviation

colWeightedSds {DelayedMatrixStats}

R Documentation

Weighted variance and weighted standard deviation

Description

Computes a weighted variance / standard deviation of a numeric vector or across rows or columns of a matrix.

Usage

colWeightedSds(x, w = NULL, rows = NULL, cols = NULL, na.rm = FALSE, ...)

colWeightedVars(x, w = NULL, rows = NULL, cols = NULL, na.rm = FALSE, ...)

rowWeightedSds(x, w = NULL, rows = NULL, cols = NULL, na.rm = FALSE, ...)

rowWeightedVars(x, w = NULL, rows = NULL, cols = NULL, na.rm = FALSE, ...)

## S4 method for signature 'DelayedMatrix'
colWeightedSds(
  x,
  w = NULL,
  rows = NULL,
  cols = NULL,
  na.rm = FALSE,
  force_block_processing = FALSE,
  ...
)

## S4 method for signature 'DelayedMatrix'
colWeightedVars(
  x,
  w = NULL,
  rows = NULL,
  cols = NULL,
  na.rm = FALSE,
  force_block_processing = FALSE,
  ...
)

## S4 method for signature 'DelayedMatrix'
rowWeightedSds(
  x,
  w = NULL,
  rows = NULL,
  cols = NULL,
  na.rm = FALSE,
  force_block_processing = FALSE,
  ...
)

## S4 method for signature 'DelayedMatrix'
rowWeightedVars(
  x,
  w = NULL,
  rows = NULL,
  cols = NULL,
  na.rm = FALSE,
  force_block_processing = FALSE,
  ...
)

Arguments

`x`	A NxK DelayedMatrix.
`w`	a vector of weights the same length as `x` giving the weights to use for each element of `x`. Negative weights are treated as zero weights. Default value is equal weight to all values.
`rows`	A `vector` indicating subset of elements (or rows and/or columns) to operate over. If `NULL`, no subsetting is done.
`cols`	A `vector` indicating subset of elements (or rows and/or columns) to operate over. If `NULL`, no subsetting is done.
`na.rm`	a logical value indicating whether `NA` values in `x` should be stripped before the computation proceeds, or not. If `NA`, no check at all for `NA`s is done. Default value is `NA` (for efficiency).
`...`	Additional arguments passed to specific methods.
`force_block_processing`	`FALSE` (the default) means that a seed-aware, optimised method is used (if available). This can be overridden to use the general block-processing strategy by setting this to `TRUE` (typically not advised). The block-processing strategy loads one or more (depending on `\link[DelayedArray]{getAutoBlockSize}()`) columns (`colFoo()`) or rows (`rowFoo()`) into memory as an ordinary base::array.

Details

The estimator used here is the same as the one used by the "unbiased" estimator of the Hmisc package. More specifically, weightedVar(x, w = w) == Hmisc::wtd.var(x, weights = w),

Value

Returns a numeric scalar.

Missing values

This function handles missing values consistently with weightedMean(). More precisely, if na.rm = FALSE, then any missing values in either x or w will give result NA_real_. If na.rm = TRUE, then all (x, w) data points for which x is missing are skipped. Note that if both x and w are missing for a data points, then it is also skipped (by the same rule). However, if only w is missing, then the final results will always be NA_real_ regardless of na.rm.

Author(s)

Peter Hickey

Examples

# A DelayedMatrix with a 'SolidRleArraySeed' seed
dm_Rle <- RleArray(Rle(c(rep(1L, 5),
                         as.integer((0:4) ^ 2),
                         seq(-5L, -1L, 1L))),
                   dim = c(5, 3))

colWeightedSds(dm_Rle, w = 1 / rowMeans2(dm_Rle))

# Specifying weights inversely proportional to rowwise means
colWeightedVars(dm_Rle, w = 1 / rowMeans2(dm_Rle))

# Specifying weights inversely proportional to columnwise means
rowWeightedSds(dm_Rle, w = 1 / colMeans2(dm_Rle))

# Specifying weights inversely proportional to columnwise means
rowWeightedVars(dm_Rle, w = 1 / colMeans2(dm_Rle))

[Package DelayedMatrixStats version 1.10.1 Index]