How do I make a best fit line? along with getting R^2 on matlab.

I am trying to make a best fit line out of a set of data for my physics class, but I don't know how to enter a table of 7 (x) and (y) values into matlab. I also don't know how to plot those data points and get a best fit linear line with them. I was told you don't use the fplot command. Also I need the coefficient of determination (R^2).

Answer 1

[Image Analyst]

To enter the values into MATLAB, you can list all 14 values (7 values for x and 7 values for y) in between brackets:

x = [1,3,4,7,13,19,42];
y = [2,4,6,8,11,36,52];

Then call plot()

plot(x, y, 'b*-', 'LineWidth', 2, 'MarkerSize', 15);

Then get a fit

coeffs = polyfit(x, y, 1);
% Get fitted values
fittedX = linspace(min(x), max(x), 200);
fittedY = polyval(coeffs, fittedX);
% Plot the fitted line
hold on;
plot(fittedX, fittedY, 'r-', 'LineWidth', 3);

[Image Analyst]

[Daniel Shub]

If you are willing to get rid of the blue line, then you can just use lsline.

[Image Analyst]

There is no lsline() in base MATLAB. If he didn't want the blue line he can simply tell plot not to use a line:

plot(x, y, 'b*', 'LineWidth', 2, 'MarkerSize', 15);

[Daniel Shub]

You are correct. The LSLINE function is part of the stats toolbox. I didn't realize that. That said the student edition comes with the stats toolbox. I don't use LSLINE much, but I find it to be pretty convenient when I do.

[10B]

Good answer Image Analyst...

Answer 2

[the cyclist]

I think the simplest way to do what you want is to use the polyfit() command. You can type

doc polyfit

at the command line to see documentation (and a simple example that you should be able to mimic). The documentation is also here:

http://www.mathworks.com/help/matlab/ref/polyfit.html

[Daniel Shub]

Since you don't need the coefficients of the line to get R^2, I think lsline is even easier for plotting the line.