I got this answer from Qbank for question ID#86819: The R^2 = (SST - SSE)/SST = RSS/SST = (20,922.5 - 8,257.374) / 20,922.5 = 0.6053. --------------- It’s wrong, isn’t it? R^2 should equal to SSE/SST, not RSS/SST Thanks.
R^2 = RSS/SST = explained vatioation/total variation = (total - unexplained)/total variation.
quechuong Wrote: ------------------------------------------------------- > I got this answer from Qbank for question > ID#86819: > > The R^2 = (SST - SSE)/SST = RSS/SST = (20,922.5 - > 8,257.374) / 20,922.5 = 0.6053. > > --------------- > > It’s wrong, isn’t it? > > R^2 should equal to SSE/SST, not RSS/SST > > Thanks. No, it’s correct. The R^2 is a number that explains how much of the variance in the dependent variable the independent variable explains. So, you find the percentage by taking the regression sum of squares and divide by the total sum of squares. The remainder (SST-RSS)/SST or SSE/SST is the variance the regression didn’t explain and is equal to 1-R^2
got it. some stat books use SSE as the “Explained sum of squares” and RSS as the “Residual sum of squares”. It’s better to stick with the CFA’s curriculum.