Apr 24

Standard Error in Linear Regression - 10 min. screencast

by David Harper, CFA, FRM, CIPM

A simple (two-variable) regression has three standard errors: one for each coefficient (slope, intercept) and one for the predicted Y (standard error of regression. In the 2007 FRM, this was called the standard error of estimate, SEE, and it often called the SEE).

Recall that while the population regression function (PRF) is singular, sample regression functions (SRF) are plural. Each sample produces a (slightly?) different SRF. So, the coefficients exhibit dispersion (sampling distribution). The standard error is the measure of this dispersion: it is the standard deviation of the coefficient.