I'm having a hard time getting conditional hope. I know that $$P(X = x | Y = y) = y^x(1-y)^{1-x}, \:\: x = \{0,1\}, \:\: 0 \leq y \leq 1.$$ Besides that, $Y \sim U[0, 1]$.

I want to get $E(Y|X=x).$

Starting from the definition of conditional probability, I arrive at

\begin{align} P(Y = y | X = x) = & \frac{P(Y=y, X=x)}{P(X=x)}\\ & \frac{P(X=x|Y=y)P(Y=y)}{P(X=x)} \end{align}

Adding in $Y$ I get that $X \sim Bern(0,5)$. That way,

\begin{align} P(Y = y | X = x) = & \: \frac{P(X=x|Y=y)P(Y=y)}{P(X=x)}\\ = & \: \frac{y^x(1-y)^{1-x}yI(0 \leq y \leq 1)}{(\frac{1}{2})^x(\frac{1}{2})^{1-x}}\\ = & \: 2y^{x+1}(1-y)^{x-1}I(0 \leq y \leq 1) \end{align}

Where is the misconception, since for $x = 0$, $Y|x=0$ is not a density?

Thanks in advance!


I think you have included an additional $y$ in the numerator and the index for $(1-y)$ seems to be not correct as well.

$$f_Y(y|X=x) = \frac{y^x(1-y)^{1-x}}{\frac12}=2y^x(1-y)^{1-x}$$


$$f_Y(y|X=0) = 2(1-y)$$ which is nonnegative and integrates to $1$.

  • $\begingroup$ True, now that I realize that I have replaced the accumulated by density. Thank you! $\endgroup$ Feb 26 '20 at 13:29

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.