1
$\begingroup$

I recently have been trying to analyze the variance of two related random variables $G$ and $F$, hoping to get a decrease of the variance when switching to the second ($F$). However, either my computations are wrong, or my intuition is -- it looks like the variance goes up. At this point, I am hoping for either finding a mistake (it goes down) or understanding why.

Let $(p_1,\dots,p_n)\in[0,1]^n$ be parameters such that $q_i=q\stackrel{\rm{}def}{=}\frac{1}{n}\sum_{i=1}^n p_i \in (0,1)$ for all $i\in[n]$. Let $X_1,\dots, X_n$ be independent Poisson random variables, where $X_i\sim\operatorname{Poisson}(p_i)$; and $Y_1,\dots,Y_n$ be independent random variables (also independent from the $X_i$'s) with $Y_i\sim\operatorname{Poisson}(q_i)$.

I also have a random variable $Y\sim\operatorname{Poisson}(q)$, independent of $(X_i)_{1\leq i \leq n}$. ($Y$ and all the $Y_i$'s are identically distributed).

Let $$G\stackrel{\rm{}def}{=} \sum_{i=1}^n \left( (X_i-Y_i)^2 - X_i - Y_i \right)$$ and $$F\stackrel{\rm{}def}{=} \sum_{i=1}^n \left( (X_i-Y)^2 - X_i - Y \right).$$

We have* $\mathbb{E} G = \mathbb{E} F = \sum_{i=1}^n (p_i-q_i)^2 $. What I am interested in is the (way messier to compute for $F$, as the terms of the sums are no longer independent) variance of both $F$ and $G$; getting closed form expression, or at least upper bounding them. I have this for $G$, but "intuitively" feel that one should get $$ \operatorname{Var} F \leq \operatorname{Var} G \tag{$\dagger$} $$ as instead of many $Y_i$ which induce fluctuations, there is only one random variable $Y$. Trying to compute it, using properties of the Poisson distribution and breaking the variance into $\mathbb{E}[ G^2] - (\mathbb{E} G)^2$ (and expanding the square of the sum in the expectation of the first term) is (a) horrendous; and (b) the result I got seems to contradict my "conjecture" $(\dagger)$.

Is there a simple way to prove/disprove what I thought, or (even better) to elegantly compute the variance to do so?

Best,

Clément.

*(unless I messed up with the statement of the problem)

$\endgroup$
  • 1
    $\begingroup$ There might be a misprint in the definition of $q_i$ (the RHS does not depend on $i$). Or do you mean $q_i=\frac1n\sum\limits_{k=1}^nq_k$? $\endgroup$ – Did Jun 20 '14 at 19:24
  • $\begingroup$ Sometimes using multiple independent and identically distributed samples will reduce variance. The most famous example is that $\frac{1}{n}\sum_{i=1}^nX_i$ has a smaller variance than $X_1$, even thought it has the same mean. $\endgroup$ – Michael Jun 20 '14 at 19:27
  • $\begingroup$ You should be able to get closed form answers for both of these. We have $Var(F) = E[F^2] - E[F]^2$. You already know $E[F]$. $\endgroup$ – Michael Jun 20 '14 at 19:31
  • $\begingroup$ @Michael: I know, I did it -- and was puzzled by the result. Hence the question, to understand it or find out if I had made a mistake. $\endgroup$ – Clement C. Jun 23 '14 at 21:57
  • $\begingroup$ @Did: the quantity $q_i$ is a constant (but I do have a conflict of notation in my question with $i$ also being the summation -- dummy -- variable). $q_i=q$ is the value obtained by "spreading uniformly" the total $p([n])$ on the $n$ elements. $\endgroup$ – Clement C. Jun 23 '14 at 21:59
1
$\begingroup$

My intuition is the other way around, because using multiple i.i.d. samples often reduces variance. Define:
\begin{eqnarray*} G_i &=& (X_i-Y_i)^2 - (X_i+Y_i)\\ F_i &=& (X_i-Y)^2 - (X_i+Y) \end{eqnarray*} Then $G=\sum_{i=1}^n G_i$ and $F = \sum_{i=1}^nF_i$. The $\{G_1, \ldots, G_n\}$ variables are independent, while the $\{F_1, \ldots, F_n\}$ variables are not. However, for each $i \in \{1, \ldots, n\}$, $F_i$ and $G_i$ are identically distributed. So $Var(F_i)=Var(G_i)$ and:
$Var(G) = \sum_{i=1}^nVar(G_i)$
$Var(F) = \sum_{i=1}^nVar(G_i) + \sum_{i\neq j} E[(F_i-E[F_i])(F_j-E[F_j])]$

Thus, $Var(F)>Var(G)$ when the $F_i$ variables are postively correlated with each other, as they probably are in this case.

You can reduce variance if you find a way of making $F_i$ samples that are negatively correlated with each other.

$\endgroup$
  • $\begingroup$ Related to Did's comment: I assume you mean that $q_i=q$ for all $i$, so $\{Y_1, \ldots, Y_n\}$ are i.i.d. random variables. My answer above assumes that. $\endgroup$ – Michael Jun 20 '14 at 21:00

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.