[GRASS-stats] Re: [GRASS-user] Testing i.pca ~ prcomp(), m.eigensystem ~ princomp()

[Nikos Alexandris]

Nikos:  
> >>> Hi Agus. The difference is:
> >>> Using SPOT (range up to max. 255):

Markus M:  
> That implied to me that the max possible value of SPOT was used, not the 
> max observed (often the max observed is also the max possible).

Right. Sorry for not being precise.


> In my experience, when comparing imagery or derived products from different 
> sensors, the least errors occur if everything is rescaled to the same 
> range, e.g. 0 - 255 for surface reflectance or -1 - 1 for NDVI, whatever 
> is convenient or appropriate.

> Note that the scale factor for MODIS is 0.0001 which would give you a 
> new range of -0.01 - 1.6 (I hope I got my math right), not 0 - 255 as 
> for e.g. SPOT or Landsat.

The thing is by multiplying by 0.0001 thing are worse concerning the
*eigenvalues* (the eigenvectors are the same):


# using the MODIS bands as they are
r.info -r mod_b2

min=0
max=5504


# use of i.pca gives
r.info -h pca_mod_b267.1

[...]
Data Description:
   generated by i.pca
Comments:
   Eigen values, (vectors), and [percent importance]:
   PC1 6307563.04 (-0.6353,-0.6485,-0.4192)[98.71%]
   PC2  78023.63 (-0.7124, 0.2828, 0.6422)[1.22%]
   PC3   4504.60 (-0.2979, 0.7067,-0.6417)[0.07%]
   

# using MODIS bands multiplied by 0.0001
r.info -r mod_b2_x

min=0
max=0.5504


# using i.pca gives
r.info -h pca.mod_x.1

[...]   
Data Description:
   generated by i.pca
Comments:
   Eigen values, (vectors), and [percent importance]:
   PC1      0.06 (-0.6353,-0.6485,-0.4192)[98.71%]
   PC2      0.00 (-0.7124, 0.2828, 0.6422)[1.22%]
   PC3      0.00 (-0.2979, 0.7067,-0.6417)[0.07%]