Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Given $x\sim \mathcal{N}(\mu=0, \sigma^2=1)$, the squared distances of the $x$ values to $\mu$ are distributed $\chi^2_1$.

I am interested in the distribution of the squared distances to an arbitrary $x$. For instance, what is the distribution of the squared distances of the observations to $x=2$?

In particular, I would like to know for a given value of $x$ what the median squared distance of the observations to that $x$ is (so, the 50% quantile of that distribution) .

share|improve this question
up vote 3 down vote accepted

You use $x$ in two ways here, so I'm replacing the arbitrary one by $x_0$. It is noncentral chi-square with 1 df and noncentrality parameter $\lambda=x_0^2$, assuming that $\mu=0$. Note that different texts use different versions of the noncentrality parameter, e.g., some people use the square root or a factor of 2. But the version I used is the same as in the R and SAS routines for this distribution.

PS the logic of my answer is this: Consider $y\sim N(x_0,1)$, and observe that the squared distance from $y$ to $0$ has the same distribution as that of the squared distance from $x$ to $x_0$.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.