Skip to main content

Timeline for Least squares residuals

Current License: CC BY-SA 4.0

7 events
when toggle format what by license comment
Sep 28, 2021 at 1:59 comment added Adrià Luz @Ejrionm Yes. I think that will also be the case even if $p=n$ (the saturated model), as long as $X$ is full rank.
Sep 27, 2021 at 18:12 comment added Ejrionm @AdriàLuz thanks, I understand the reasoning, but I'd like to have some math intuition, so you're saying that in the case of $p>n$ we have $X \hat{\beta}_i = y_i$?
Sep 27, 2021 at 17:04 comment added Adrià Luz @AdamO Makes perfect sense, thanks.
Sep 27, 2021 at 16:56 comment added AdamO You actually need the rank of $X$ to be bigger than $n$ to guarantee perfect prediction. Otherwise, the span of $X$ may be less is required to express each $Y$ exactly as a linear combination of the rows of $X$.
Sep 27, 2021 at 16:51 comment added Adrià Luz @AdamO I was thinking about the number of parameters being estimated here - so it'd be the dimension of $X$. Please let me know if that's not correct.
Sep 27, 2021 at 16:49 comment added AdamO Is $p$ the dimension of $X$ or the rank?
Sep 27, 2021 at 16:44 history answered Adrià Luz CC BY-SA 4.0