# colDevs: Calculate column deviations from central values In heplots: Visualizing Hypothesis Tests in Multivariate Linear Models

## Description

`colDevs` calculates the column deviations of data values from a central value (mean, median, etc.), possibly stratified by a grouping variable.

Conceptually, the function is similar to a column-wise `sweep`, by group, allowing an arbitrary `center` function.

## Usage

 `1` ```colDevs(x, group, center = mean, ...) ```

## Arguments

 `x` A numeric data frame or matrix. `group` A factor (or variable that can be coerced to a factor) indicating the membership of each observation in `x` in one or more groups. If missing, all the data is treated as a single group. `center` A function used to center the values (for each group if `group` is specified. The function must take a vector argument and return a scalar result. `...` Arguments passed down

## Details

Non-numeric columns of `x` are removed, with a warning.

## Value

A numeric matrix containing the deviations from the centering function.

## Author(s)

Michael Friendly

`colMeans` for column means,

`sweep`

## Examples

 ``` 1 2 3 4 5 6 7 8 9 10 11``` ```data(iris) Species <- iris\$Species irisdev <- colDevs(iris[,1:4], Species, mean) irisdev <- colDevs(iris[,1:4], Species, median) # trimmed mean, using an anonymous function irisdev <- colDevs(iris[,1:4], Species, function(x) mean(x, trim=0.25)) # no grouping variable: deviations from column grand means # include all variables (but suppress warning for this doc) irisdev <- suppressWarnings( colDevs(iris) ) ```

### Example output

```Loading required package: car