The degrees of freedom in a multiple regression equals $N-k-1$, where $k$ is the number of variables.

Does $k$ include the response variable (i.e., $Y$)? For example, in the model $Y = B_0 + B_1X_1 + B_2X_2$, then does $k = 3$ (i.e., 1 df each for $Y$, $X_1$, & $X_2$)?

  • 2
    $\begingroup$ I don't know where you found this quote, but it sure is poorly phrased. $\endgroup$ – Patrick Coulombe Feb 22 '14 at 3:40

It's the number of predictor (x) variables; the additional -1 in the formula is for the intercept - it's an additional predictor. The Y doesn't count. So in your example $k=2$ and the error df is $N-3$

  • 5
    $\begingroup$ Another (ultimately equivalent) way to think about this is that you use 1 df for each parameter estimate (ie, $\hat\beta$), plus 1 df for the mean of the response (ie, $\bar y$), since the intercept is determined once you have $({\bf\bar x}, \bar y)$ and the slopes. $\endgroup$ – gung - Reinstate Monica Feb 22 '14 at 3:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.