Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
NCTM or The Math Forum.
|
|
|
|
Curvefitting
Posted:
Sep 30, 1996 3:38 PM
|
|
Hi, as a new user of Matlab, I have been faced with the following
problem. I am doing error propagation, and lets say that I have the following
situation:
1) I make a scatterplot of 20 points on a non-log, x-y plot.
2) I use c2=curvefit(x,y,1) to fit the least squares line
3) I have to use the slope of this line in further calculations, and would
like to know how to take the error of the slope into account. I know
that it is not simply corrcoef(x,y) but that I need something like:
The slope = 2345.6 +/- 43.3
How can I get a +/- like shown above? I looked through Traver's Tutorial, as
well as the one by Sigmon, and the MIT help docs, and couldn't figure out how
to do this. If someone could help, I would greatly appreciate it.
Koichi Kunitake
<kkunitak@mit.edu>
|
|
|
|
