1
$\begingroup$

given that $X_1, X_2, X_3$ are independent and identically distributed, $X_1 \sim N(0,1)$.

I tried to calculate the cumulative distribution function of Y: \begin{align} P(Y\leq y) &= \underset{\frac{x_1+x_2x_3}{\sqrt{1+x_1^2}}\leq y}{\iiint}f(x_1)f(x_2)f(x_3)\mathrm{d}x_1\mathrm{d}x_2\mathrm{d}x_3\\ &= \int_{-\infty}^\infty \mathrm{d}x_1 \underset{x_2x_3\leq y\sqrt{1+x_1^2}-x_1}{\iint}f(x_1)f(x_2)f(x_3)\mathrm{d}x_2\mathrm{d}x_3\\ &= \cdots \end{align} and then derive the probability density function of $Y$. But I can't figure out the above integral.

$\endgroup$
1
$\begingroup$

OP asks:

Prove that $Y = \frac{X_1+X_2*X_3}{\sqrt{1+X_1^2}}$ obeys normal distribution

How about a proof that it doesn't?

Here is a quick Monte Carlo check of the empirical pdf of $Y$:

enter image description here

which is decidedly not Normal.

What is the source of your question?

$\endgroup$
  • $\begingroup$ My junior classmate asked me this question. Since it's false, should I delete this question, or modify it? $\endgroup$ – useprxf Nov 15 '14 at 2:02

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.