Timeline for Conditional independence of the response variable, regression analysis
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 15, 2022 at 13:57 | vote | accept | Maximilian | ||
| Dec 15, 2022 at 8:19 | comment | added | Christoph Hanck | I deleted and gathered my comments in an expanded answer below. | |
| Dec 15, 2022 at 8:19 | answer | added | Christoph Hanck | timeline score: 1 | |
| Dec 14, 2022 at 18:54 | comment | added | Maximilian | thank you very much. Does this fact give rise to any further implication? | |
| Dec 14, 2022 at 15:20 | comment | added | Maximilian | First of all, thank you very much for your comment. What do you mean by constant regressors? The book keeps saying that also when it talks about generalized linear models (GLMs): For given covariates $xi= (1,x_{i1},...,x_{ik} )'$, the response variables are (conditionally) independent and the (conditional) density of $y_i$ belongs to an exponential family with: \begin{equation} f(y_i,\theta_i) = exp \left ( \frac{y_i \theta_i - b(\theta_i)}{\phi}w_i + c(y_i, \phi,w_i) \right) \end{equation} | |
| Dec 14, 2022 at 10:19 | history | asked | Maximilian | CC BY-SA 4.0 |