Reposted from math stackexchange (https://math.stackexchange.com/questions/2779699/constant-concentration-for-chi-square-variables) as suggested by another user.

I would like to have a certain concentration inequality for chi square variables with $k$ degrees of freedom. As referenced in What are the sharpest known tail bounds for $\chi_k^2$ distributed variables?, Laurant and Massart give as a corollary that $$ \Pr\left(\left\lvert X-\mathbb E(X)\right\rvert\geq 2\sqrt{kx}+2x\right)\leq 2\exp(-x). $$ However, I only care about the case where the right hand side is constant, say $1/10$ (so $x\approx 3$), and I would like a weaker dependence on $k$, say $k^{1/4}$ instead of $k^{1/2}$. I only care about the asymptotic order of $k$, so anything $O(k^{1/2-\varepsilon})$ would be great. Could anyone suggest any results/approaches, or could it be impossible? Thank you!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.