Timeline for Showing that $\sum_{i=1}^n (y_i-\hat{y_i})(\hat{y_i} - \bar{y}) = 0$ for the generalized linear model
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 31, 2018 at 18:39 | vote | accept | Rebellos | ||
| Oct 30, 2018 at 21:24 | comment | added | Rebellos | @MartijnWeterings Then how should be the correct approach ? | |
| Oct 30, 2018 at 21:19 | history | edited | user158565 | CC BY-SA 4.0 |
added 119 characters in body
|
| Oct 30, 2018 at 21:10 | comment | added | Sextus Empiricus | The conclusion might be correct but the $H$ that you use is the perpendicular projection matrix (shortest distance) which associates to least squares and Gaussian error distribution. It is not in general related to generalized linear models. | |
| Oct 30, 2018 at 21:07 | history | edited | user158565 | CC BY-SA 4.0 |
added 1 character in body
|
| Oct 30, 2018 at 21:07 | comment | added | user158565 | $H=X(X'X)^{-1}X'$. I do not know it belongs to OLS or GLM or both. I think this conclusion just correct for general linear model. | |
| Oct 30, 2018 at 20:56 | comment | added | Sextus Empiricus | Isn't the H matrix that you use for OLS instead of GLM? | |
| Oct 30, 2018 at 20:50 | vote | accept | Rebellos | ||
| Oct 30, 2018 at 21:23 | |||||
| Oct 30, 2018 at 20:41 | history | edited | user158565 | CC BY-SA 4.0 |
added 1 character in body
|
| Oct 30, 2018 at 20:14 | history | answered | user158565 | CC BY-SA 4.0 |