Loading [MathJax]/jax/output/HTML-CSS/jax.js

Friday, 2 December 2016

Moments of a weighted sum of distributions

Let X be a random variable with distribution g(x)=ΣNi=1λifi(x), where each fi is a probability distribution for the RV Xi (with mean μi and variance σ2i), λi0 and ΣNi=1λi=1.

We determine the mean, E[X]=μ and variance, V[X]=σ2, of X in terms of those of the Xi.

We have
μ=E[X]=E[ΣNi=1λiXi]=ΣλiE[Xi]=ΣNi=1λiμi
by linearity.

Then on expanding the square we have
σ2=V[X]=E[(Xμ)2]=E[X2]μ2,
but that isn't really any help to us, because we haven't determined E[X2].

Alternatively,
σ2=dx(xμ)2f(x)=dx(xμ)2Σiλifi(x)=Σiλi(xμ)2fi(x)
=Σiλidxfi(x)(xμi+μiμ)2
=Σiλidxfi(x)[(xμi)2+2(xμi)(μiμ)+(μiμ)2]

=Σiλi[dxfi(x)(xμi)2+2(μiμ)dxfi(x)(xμi)+(μiμ)2dxfi(x)]

=ΣNi=1λi(E[(Xiμi)2]+2(μiμ)(E[Xi]μi)+(μiμ)2)

=ΣNi=1λi(V[Xi]+(μiμ)2)
ΣiλiV[Xi]


No comments:

Post a Comment