The Normal distribution of generating data g(y) and specified model f(y) is-
g(y)~N(m,t2)
f(y)~N(μ,o2)
The probability density function is-
Y=2π1e2−x2
logY=log2π1+loge2−x2=log2π1+2−x2 −(1)
So E(logY)=∫0rxlogYdx
=∫0rxlog2π1+2−x3dx=2x2log2π1∣0r−8x4∣0r=2r2log2π1−8r4=−log(2rt2)−1
Hence E(logY)=−log(2rt2)−1
Comments