# Derivation of standard error of beta in simple linear regression

Countless web pages show the equation for the standard error of the slope in a simple linear regression. For example:

SE = sb1 = sqrt [ Σ(yi - ŷi)2 / (n - 2) ] / sqrt [ Σ(xi - x)2 ]


However, I have not been able to find a single web page that derives this equation. The derivation for this equation is extremely elusive. It's not on Wikipedia, not on countless university course web sites. Can someone point me to the actual derivation of this?

-
Have you seen this? It's based on the Student $t$ distribution... –  Guess who it is. Jul 19 '12 at 11:43