Timeline for Estimating quantiles with linear regression?
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 14, 2016 at 10:13 | comment | added | DeltaIV | ctd...shouldn't we be able to estimate $y_q(x)$? | |
| Sep 14, 2016 at 10:12 | comment | added | DeltaIV | Hi, thanks for the answer, but I haven't talked about an interval for $y_q(x)$ (not sure what the $^*$ means). I have talked about an estimate for $y_q(x)$: I should have written $\hat{y}_q(x)$ to make that clear. Probably the prediction interval is not the right tool, but I'm sure there's a way to compute that estimate in the frequentist paradigm. The reason is clear: with the simple linear regression model, $y(x) \sim N(\beta_0+\beta_1x,\sigma^2)$. We have estimates for $\beta_0$, $\beta_1$ and $\sigma^2$, and we know that the distribution is Gaussian. Then why ctd... | |
| Sep 13, 2016 at 19:58 | review | First posts | |||
| Sep 13, 2016 at 20:00 | |||||
| Sep 13, 2016 at 19:56 | history | answered | Tessellator | CC BY-SA 3.0 |