Timeline for How does R find the dispersion parameter in a GLM?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 3, 2021 at 9:34 | vote | accept | userpisquared | ||
| Jun 2, 2021 at 22:26 | history | edited | Ben Bolker | CC BY-SA 4.0 |
added 359 characters in body
|
| Jun 2, 2021 at 22:20 | comment | added | Ben Bolker | Effectively, yes (see my edits). | |
| Jun 2, 2021 at 22:20 | history | edited | Ben Bolker | CC BY-SA 4.0 |
added 359 characters in body
|
| Jun 2, 2021 at 22:08 | comment | added | AdamO | Would "working" residuals mean the residuals using the "working" (co)variance matrix? i.e. for a Poisson GLM, the Pearson residuals defined by: $r_i = (Y_i - \mu_i)/v_i$ with $v_i = \mu_i, i= 1, \ldots, n$. | |
| Jun 2, 2021 at 22:03 | history | answered | Ben Bolker | CC BY-SA 4.0 |