Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. 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

I'm having trouble wrapping my brain around this idea.

Suppose we have $X$ and $X'$ which are IID continuous random variables with conditional cdfs:

$F_{+}(x) = P(X \leq x | \epsilon = 1)$

$F_{-}(x) = P(-X \leq x | \epsilon = -1)$

Where $\epsilon = sign(X)$.

Suppose further that $P(\epsilon = 1) = p$.

The probability I am looking to compute is:

$P(X' < -X | \epsilon = 1 \wedge \epsilon' = -1)$

I want to know in terms of $F_+(x)$ and $F_{-}(x)$ (or possibly their derivatives) and p what this quantity might be. My instinct was to say 1/2 but I know that isn't necessarily right. I've basically reached a gap in understanding regarding the signed rank test statistic and understanding this quantity would really help to get me over the hump. Thanks a lot for any advice..

share|cite|improve this question
up vote 2 down vote accepted

The probability to be computed is $$ \iint\mathbf 1_{0\leqslant x\lt y}\mathrm dF_+(x)\mathrm dF_-(y)=\int_0^{+\infty}F_+(y)\mathrm dF_-(y)=1-\int_0^{+\infty}F_-(x)\mathrm dF_+(x). $$

share|cite|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.