I am looking for an elementary explanation of why a loaded coin gets more and less than the expected number of heads approximately equiprobably, in other words, mean=median.

Mathematically speaking, if $X\sim B(n,p)$ is a Binomial random variable, then $P(X<np)\approx P(X>np)$ for large $n$.

When $p=\frac12$, this is obvious because of the exact symmetry of the distribution around $\frac{n}{2}$.

For a general $0<p<1$ this follows from convergence of $X$ to the Gaussian Normal distribution.

Is there an elementary intuitive explanation?

  • $\begingroup$ interesting question. for a general r.v. $X$, the mean and the median are not necessarily the same, i.e. $P(X > E[X]) \neq P(X < E[X])$. i suspect we do have to pull in the CLT to explain why mean = median for $X = B(n,p)$. but i would love to see an alternate "elementary intuitive" explanation. $\endgroup$ – antkam Feb 7 at 18:54

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.