I'm trying to answer the following question from Larry Wassermans book on statistical inference.

enter image description here

My question is how did they arrive at the Markov bound, it does not seem like the normal form of the Markov inequality i.e. $P(Z > t) \leq \frac{\mathbb{E}(Z)}{t}$. Also how could we analytically calculate $\mathbb{E}(|Z|^k)$.

  • $\begingroup$ Apply the "normal form" of the equality to the random variable $|Z|^k.$ $\endgroup$ – whuber May 21 '19 at 12:04

First note that the Markov inequality applies to non-negative random variables; you can't apply it directly to $Z$.

Let $Y=|Z|^k$ for $k>0$, which is non-negative. Now apply the Markov inequality to $Y$, then relate that back to a probability statement about $|Z|$. (Edit: as whuber already noted in comments; not sure how I missed that)

As for evaluating $E(|Z|^k)$, there's several ways to approach it. Let's take a fairly straightforward one -- just write the integral, use the symmetry of $|Z|$ to write it in terms of an integral on the positive half line, and then make an obvious substitution to get a gamma function.


Your Answer

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

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