[R-sig-Geo] Residual maps in R

[Antonio Serrano]

Hello, John:

   Obviously, you cannot print all residuals in the same pixel, so, you have to think on a statistics derived from the residuals that takes just one value.

   This statistic should be descriptive enough for your purpouses. 
   
   For example, if you want to "see" on the map, if the residuals are autocorrelated, you can plot using two colours: one for not autocorrelated residuals, and another for autocorrelated ones. And this could be choose using a hypothesis test with some confidence level.

   If you also want to "show" some other characteristic of the residuals, you have to look for another descriptive statistic.

  Hope this helps.


Antonio Serrano
aasdelat at aim.com
ن

 

 

-----Original Message-----
From: John Wasige <johnwasige at gmail.com>
To: r-sig-geo <r-sig-geo at r-project.org>
Sent: Sun, May 31, 2015 1:35 pm
Subject: [R-sig-Geo] Residual maps in R


Hello guys, Could somebody help with an Idea on how I can generate residual
maps
from multiple
​linear ​
regression model of raster stack time series in
R.
Thanks

John

	[[alternative HTML version
deleted]]

_______________________________________________
R-sig-Geo mailing
list
R-sig-Geo at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-geo



	[[alternative HTML version deleted]]