Timeline for Conditional expectation of (degenerate) trivariate normal?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 7, 2020 at 13:20 | history | edited | Richard Hardy |
edited tags
|
|
| Oct 26, 2019 at 4:58 | comment | added | Glen_b | Yes, the formula for conditional expectation should work as long as you use it correctly (including not setting correlations to 1 that aren't 1). | |
| Oct 25, 2019 at 21:56 | comment | added | carlo | I don't know it, but... why not? | |
| Oct 25, 2019 at 21:46 | comment | added | Adam | I see. Thank you. And what about using the formula for the conditional expectation? Is that OK even though C is a function of A and B? | |
| Oct 25, 2019 at 19:15 | comment | added | carlo | just compute it from variances and covariances: $Cov(A, C) = Var(A)$, $Cov(B, C) = Var(B)$, there is always some variability in C that can't be explained by A or B alone, you need both. | |
| Oct 25, 2019 at 18:43 | comment | added | Adam | It isn't 1? Then what is it? I thought since C was a linear combination of A and B, then the correlation with A or B would be 1. | |
| Oct 25, 2019 at 18:01 | comment | added | carlo | those correlations are not 1 | |
| Oct 25, 2019 at 16:37 | history | asked | Adam | CC BY-SA 4.0 |