1

I'm trying to determine the distribution of $Z^2$ where $Z \sim N(0,1)$. I'm not really sure even how to start, is it ok to just multiply the density functions? May I need to use the MGF?

Michael Hardy
  • 1
  • 30
  • 276
  • 565
lithiium
  • 121
  • 3
  • [Possible Duplicate](http://math.stackexchange.com/questions/101062/is-the-product-of-two-gaussian-random-variables-also-a-gaussian) – Mark Viola Sep 10 '15 at 17:03
  • possible duplicate of [Probability density function of $X^2$ when $X$ has $N(0,1)$ distribution](http://math.stackexchange.com/questions/368042/probability-density-function-of-x2-when-x-has-n0-1-distribution) –  Sep 10 '15 at 22:15

1 Answers1

4

You can't just multiply the density functions, but you can calculate the CDF of $Z^2$ in terms of $\Phi(x) = P(Z \le x)$. Note that $$P(Z^2 \le x) = P(|Z| \le \sqrt{x}) = P(-\sqrt{x} \le Z \le \sqrt{x}) = \Phi(\sqrt{x}) - \Phi(-\sqrt{x})$$ holds for any $x \ge 0$. From this you can calculate the density by deriving the CDF.

The distribution of $Z^2$ is called chi-squared distribution with $1$ degree of freedom. The corresponding notation is $Z^2 \sim \chi^2_1$.

Did
  • 271,033
  • 27
  • 280
  • 538
Dominik
  • 19,163
  • 1
  • 24
  • 46