Work out residual analysis instantly with clear inputs, formula shown and shareable results.
A residual is the observed value minus the fitted value. Their sum of squares drives the standard error of the estimate √(SSE/(n − 2)), and comparing SSE to the total sum of squares gives R².
Residual
eᵏ = yᵏ − (a + b·xᵏ)
Standard error
s = √(SSE / (n − 2)), R² = 1 − SSE/SST
The residuals are −0.8, 0.6, 1.0, −0.6 and −0.2, giving SSE = 2.4 against SST = 6, so R² = 0.6.
Random scatter about zero. Any pattern or fanning indicates the model is misspecified.