Geografic-Information-System/scripts/r.regression.line/r.regression.line.html

<H2>DESCRIPTION</H2>

<EM>r.regression.line</EM> Calculates linear regression from two raster maps, 
according to the formula y = a + b*x, where x and y represent raster maps. 
Optionally saves regression coefficients to an ASCII file. 
The result includes the following coefficients:
offset/intercept (a) and gain/slope (b), residuals (R),
number of elements (N), means (medX, medY), standard deviations
(sdX, sdY), and the F test for testing the significance of the
regression model as a whole (F).

<H2>NOTES</H2>
The flag <em>-s</em> select the slower method (applies to FP maps only)
which writes out all pixel values individually to the temporary file.
The results for offset/intercept (a) and gain/slope (b) are then
identical to that obtained from R-stats's lm() function. 

<H2>EXAMPLE</H2>

Comparison of the old and the new DEM in Spearfish:
<div class="code"><pre>
g.region rast=elevation.10m -p
r.regression.line map1=elevation.dem map2=elevation.10m
</pre></div>
<p>

Using the script style flag AND <em>eval</em> to make results
available in the shell:
<div class="code"><pre>
g.region rast=elevation.10m -p
eval `r.regression.line -g map1=elevation.dem map2=elevation.10m`
echo $a
479.615

echo $b
0.645631

echo $R
0.804441
</pre></div>


<H2>AUTHOR</H2>

Dr. Agustin Lobo - alobo at ija.csic.es<BR>
Updated to GRASS 5.7 Michael Barton, Arizona State University<BR>
Script style output Markus Neteler

<p><i>Last changed: $Date$</i>