pearson.dist: Distance based on Pearson's R squared

In hyperSpec: Work with Hyperspectral Data, i.e. Spectra + Meta Information (Spatial, Time, Concentration, ...)

Description

The calculated distance is D^2 = (1 - COR (x')) / 2

Usage

pearson.dist(x)

Arguments

x

a matrix

Details

The distance between the rows of x is calculated. The possible values range from 0 (prefectly correlated) over 0.5 (uncorrelated) to 1 (perfectly anti-correlated).

Value

distance matrix (distance object)

Author(s)

C. Beleites

References

S. Theodoridis and K. Koutroumbas: Pattern Recognition, 3rd ed., p. 495

See Also

as.dist

Examples

pearson.dist (flu [[]])
pearson.dist (flu)

Example output

Loading required package: lattice
Loading required package: grid
Loading required package: ggplot2
Package hyperSpec, version 0.98-20161118

To get started, try
   vignette ("introduction", package = "hyperSpec")
   package?hyperSpec 
   vignette (package = "hyperSpec")

If you use this package please cite it appropriately.
   citation("hyperSpec")
will give you the correct reference.

The project homepage is http://hyperspec.r-forge.r-project.org


             1            2            3            4            5
2 0.0006321414                                                    
3 0.0004898572 0.0002887337                                       
4 0.0004424217 0.0002664884 0.0001705457                          
5 0.0004852460 0.0002368675 0.0001909183 0.0001149165             
6 0.0004242441 0.0002416168 0.0001591670 0.0001208129 0.0001102328
             1            2            3            4            5
2 0.0006321414                                                    
3 0.0004898572 0.0002887337                                       
4 0.0004424217 0.0002664884 0.0001705457                          
5 0.0004852460 0.0002368675 0.0001909183 0.0001149165             
6 0.0004242441 0.0002416168 0.0001591670 0.0001208129 0.0001102328

hyperSpec documentation built on May 2, 2019, 5:45 p.m.