Home > wafo > wstats > iqr.m

# iqr

## PURPOSE

Computes the Inter Quartile Range

r = iqr(X,dim)

## DESCRIPTION

``` IQR Computes the Inter Quartile Range

CALL:  r = iqr(X,dim);

r = abs(diff(wquantile(X,[0.25 .75]))),
X = data vector or matrix
dim = dimension to sum across. (default 1'st non-singleton
dimension of X)
IQR is a robust measure of spread.
The use of interquartile range guards against outliers if
the distribution have heavy tails.

Example:
R=wgumbrnd(2,2,[],100,2);
iqr(R)

## CROSS-REFERENCE INFORMATION

This function calls:
 wquantile Empirical quantile (percentile). diff Difference and approximate derivative. error Display message and abort function. ipermute Inverse permute array dimensions. permute Permute array dimensions.
This function is called by:

## SOURCE CODE

```001 function r = iqr(X,dim)
002 %IQR Computes the Inter Quartile Range
003 %
004 % CALL:  r = iqr(X,dim);
005 %
006 %        r = abs(diff(wquantile(X,[0.25 .75]))),
007 %        X = data vector or matrix
008 %      dim = dimension to sum across. (default 1'st non-singleton
009 %                                              dimension of X)
010 % IQR is a robust measure of spread.
011 % The use of interquartile range guards against outliers if
012 % the distribution have heavy tails.
013 %
014 % Example:
015 %   R=wgumbrnd(2,2,[],100,2);
016 %   iqr(R)
017 %
019
020 % Tested on: Matlab 5.3
021 % History:
022 % revised pab 24.10.2000
023
024 error(nargchk(1,2,nargin))
025 sz = size(X);
026 if nargin<2|isempty(dim),
027   % Use 1'st non-singleton dimension or dimension 1
028   dim = min(find(sz~=1));
029   if isempty(dim), dim = 1; end
030 end
031
032 if dim~=1,
033   iorder=1:length(sz);
034   tmp=iorder(dim);
035   iorder(dim)=iorder(1);
036   iorder(1)=tmp;
037   X = permute(X,iorder);
038 end
039 r = abs(diff(wquantile(X,[0.25 0.75])));
040
041 if dim~=1,
042   iorder=1:length(sz);
043   tmp=iorder(dim);
044   iorder(dim)=iorder(1);
045   iorder(1)=tmp;
046   r=ipermute(r,iorder);
047 end
048
049
050 %sz(dim)=sz(dim);
051
052
053
054```

Mathematical Statistics
Centre for Mathematical Sciences
Lund University with Lund Institute of Technology

Comments or corrections to the WAFO group

Generated on Thu 06-Oct-2005 02:21:16 for WAFO by m2html © 2003