Uneven Spread
Least squares assumes the scatter around the line is equally wide everywhere. Fit an ordinary least squares line to the points (x[i], y[i]) and return the p-value of the Breusch-Pagan test for uneven scatter (use the first, Lagrange multiplier, version of the p-value).
Example 1
x [1,2,3,4,5,6,7,8]
y [1.1,1.9,3.2,3.7,5.9,4.8,9.1,5.5]
returns 0.028520357309904452
The misses grow as x grows, and the small p-value says so.
Constraints
8 <= len(x) <= 60- The points are not exactly on a line
Write it in your browser, against the clock. The model solution, stepped through line by line, comes after.