Finding conditional pdf, conditional expectation, and conditional variance

65 Views Asked by At

Given

\begin{align*} f(x, y) = \begin{cases} 2x & \text{ if } 0 < x < 1, \hspace{0.3cm} x < y < x + 1 \\ 0 & \text{ otherwise,} \end{cases} \end{align*}

(a) Find the conditional pdf $f_{Y \mid X}(y \mid x)$ of $Y$ given $X = x$.

(b) Find the conditional expectation $\mathbb{E}[Y \mid X = x]$ of $Y$ given $X = x$

(c) Find the conditional variance $\text{Var}(Y \mid X = x)$ of $Y$ given $X = x$.


My try:

(a) $$f_{Y \mid X}(y \mid x) = \frac{f(x, y)}{f_{X}(x)} = \frac{2x}{\int_{x}^{x + 1} 2x \mathop{dy}} = \frac{2x}{2x} = 1$$

for $0 < x < 1$

(b) $\mathbb{E}[Y \mid X = x]$ is computed as follows:

$$\int_{x}^{x + 1} y \mathop{dy} = \boxed{\frac{2x + 1}{2}}$$

(c) First find the second moment

$$\mathbb{E}[Y^{2} \mid X = x] = \int_{x}^{x + 1} y^{2} \mathop{dy} = \frac{(x + 1)^{3} - x^{2}}{3} = \frac{3x^2 + 3x + 1}{3}$$ Therefore,

$$ \begin{align*} \text{Var}(Y \mid X = x) = \mathbb{E}[Y^2 \mid X = x] - (\mathbb{E}[Y \mid X = x])^{2} = \frac{3x^2 + 3x + 1}{3} - \frac{4x^2 + 4x + 1}{4} \end{align*} $$


Did I solve this problem correctly?

1

There are 1 best solutions below

8
On BEST ANSWER

Use indicator functions while writing density functions to keep track of the support of the distributions.

One can directly see that the joint density factors as

\begin{align} f(x,y)&=2x\,\mathbf1_{0<x<1\,,\,x<y<x+1} \\&=\underbrace{\mathbf1_{x<y<x+1}}_{f_{Y\mid X}(y)}\,\underbrace{2x\,\mathbf1_{0<x<1}}_{f_X(x)} \end{align}

This shows that $Y\mid X$ has a uniform distribution over $(x,x+1)$ for each $0<x<1$.

It follows that for each $0<x<1$, $$E\left[Y\mid X=x\right]=\frac{2x+1}{2}$$

and $$\operatorname{Var}\left[Y\mid X=x\right]=\frac{1}{12}$$