Update linalg.rst

Complemented linreg() documentation

doc/stdlib/linalg.rst

@@ -440,9 +440,16 @@ Linear algebra functions in Julia are largely implemented by calling functions f
 
    Concatenate matrices block-diagonally. Currently only implemented for sparse matrices.
 
-.. function:: linreg(x, y)
-
-   Determine parameters ``[a, b]`` that minimize the squared error between ``y`` and ``a+b*x``.
+.. function:: linreg(x, y) -> [a; b]
+
+   Linear Regression. Returns ``a`` and ``b`` such that ``a+b*x`` is the closest line to the given points ``(x,y)``. In other words, this function determines parameters ``[a, b]`` that minimize the squared error between ``y`` and ``a+b*x``. 
+   **Example**::
+      julia> using PyPlot;
+      julia> x = float([1:12]);
+      julia> y = [5.5; 6.3; 7.6; 8.8; 10.9; 11.79; 13.48; 15.02; 17.77; 20.81; 22.0; 22.99];
+      julia> a, b = linreg(x,y); # Linear regression
+      julia> plot(x, y, "o"); # Plot (x,y) points
+      julia> plot(x, [a+b*i for i in x]); # Plot the line determined by the linear regression
 
 .. function:: linreg(x, y, w)