FRM 2008 Early Bird - Episode #3

An introduction to (refresher on) linear regression. The emphasis here is on SSR + SSE = SST. The coefficient of determination = SSR/SST = [correlation coefficient]^2. Further, I emphasize the standard error of the estimate (SEE). This is analogous to the standard deviation; it captures the dispersion of actual observations from the "predicted Y" line.

(20 min.)