Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

I used to think that the following held true:

If $Y\sim \chi^2$, then $\frac{1}{Y}\sim \operatorname{inv}\chi^2$, the inverse $\chi^2$-distribution. Let $\chi^2_\alpha$ denote the $\alpha$-quantile of $Y$, then $\frac{1}{\chi^2_\alpha}$ is the $\alpha$-quantile of $\frac{1}{Y}$, meaning $$P\left(Y\leq \chi^2_\alpha\right)=P\left(\frac{1}{Y}\leq\frac{1}{\chi^2_\alpha}\right)=\alpha.$$ Now I figured out that this cannot be true, right? But what is the relationship between the two quantiles then? (Or is it true after all?)

share|improve this question
add comment

1 Answer 1

up vote 2 down vote accepted

You need to change "$\le$" to "$\ge$": $$ \Pr\left(Y\le\chi^2_\alpha\right) = \Pr\left(\frac 1 Y \ge \frac{1}{\chi^2_\alpha}\right). $$ (The fact that $Y$ is always positive is essential here; this inversion of inequalities doesn't happen if the number on one side of the inequality is positive and the one on the other side is negative.)

share|improve this answer
add comment

Your Answer

 
discard

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.