n*******3
发帖数: 313 | 1 if X is a random variable with E(X) and V(X) known. what is the E(logX) and
V(logX)? Thanks in advance~~ |
l*******l
发帖数: 204 | 2 No. But can be approximate by delta method |
q********i
发帖数: 795 | 3 泰勒级数展开
E(logX)＝log(E(X))-1/(2E(X)^2)*Var(X)
V(logX)=1/E(X)^2*Var(X) |
B*****t
发帖数: 68 | 4 Your answers were not correct. Take the lognormal for example.
【在 q********i 的大作中提到】
: 泰勒级数展开
: E(logX)＝log(E(X))-1/(2E(X)^2)*Var(X)
: V(logX)=1/E(X)^2*Var(X)
|
w*s
发帖数: 272 | 5 Replica theorem
and
【在 n*******3 的大作中提到】
: if X is a random variable with E(X) and V(X) known. what is the E(logX) and
: V(logX)? Thanks in advance~~
|
