2
$\begingroup$

from https://arxiv.org/pdf/1401.0118.pdf

If we have a function $J(X,Y)$ of two random variables $X$ and $Y$ and we want to compute the expectation $\mathbb E_{p(X,Y)}[J(X,Y)]$.

We define $\hat J(X)= \mathbb E_{p(Y)}[J(X,Y)\mid X]$.

Note that: $$\mathbb E_{p(X,Y)}[J(X,Y)] = \mathbb E_{p(X)} [\hat J(X)]$$

So we can use $\hat J(X)$ instead of $J(X, Y)$ in a Monte-Carlo Estimate.

For the variance holds (variance reduction) $$ var(\hat J(X)) = var(J(X,Y)) - \mathcal E[(J(X,Y) - \hat J(X))^2] $$

Here I have two questions:

  • How can we proof that (variance reduction)? In the paper no proof is given.

Thanks.

$\endgroup$
2
  • 1
    $\begingroup$ can you be a bit more specific about your second question so I can improve my answer to your question? $\endgroup$ Dec 11 '18 at 21:02
  • $\begingroup$ Thank you very much. I finally got it. So the second question is not important any more. $\endgroup$ Dec 14 '18 at 16:35
2
$\begingroup$

The variance reduction follows from the the law of total variance. Suppose that $W,Z$ are two random variables, then it follows that $$ \mathbb{V}(W)=\mathbb{V}(\mathbb{E}(W\vert Z))+\mathbb{E}(\mathbb{V}(W\vert Z)) $$ then, replace $W$ by $J(X,Y)$ and $\mathbb{E}(W\vert Z)$ by $\hat{J}(X)$ and we obtain: $$ \mathbb{V}(J(X,Y))=\mathbb{V}(\hat{J}(X))+\mathbb{E}(\mathbb{V}(J(X,Y)\vert X)) $$ Notice that the second summand on the right hand side is given by $$\mathbb{V}(J(X,Y)\vert X)=\mathbb{E}(J(X,Y)^2\vert X)-(\mathbb{E}J(X,Y)\vert X)^2=\mathbb{E}(J(X,Y)^2\vert X)-\hat{J}(X)^2 $$ plug into the ANOVA identity, solve with respect to $\mathbb{V}(\hat{J}(X)$ to obtain $$ \mathbb{V}(\hat{J}(X)=\mathbb{V}(J(X,Y))-\left(\mathbb{E}(J(X,Y)^2)-\mathbb{E}(\hat{J}(X)^2)\right)=\mathbb{V}(J(X,Y))-\mathbb{E}\left(\left(J(X,Y)-\hat{J}(X)\right)^2\right) $$ as desired.

Hope this helps.

$\endgroup$
1
$\begingroup$

I have not read the paper but the variance reduction provided by an iid sample is obvious from the variance Pythagorean decomposition and less obvious for a two-stage Gibbs sampler (Liu, Wong & Kong, 1994). For a general MCMC chain there is no reason to see variance reduction due to the correlation between the elements of the chain (Liu, Wong & Kong, 1995).

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.