Let $G$ be the whole. Let $F \subset G$. I have estimated a probability $\hat p = 0.195$ for a random variable $X \in F$. The real $p$, however, is $0.2$. I want to compute the standard deviation $\sigma$ of $\hat p$ knowing the real $p$. I don't understand what is asked in the first place. As far as I understand standard deviation is the average deviation from the expected value when I continuously perform my experiment. A first thought that comes to mind is compute $\sigma$ for $p$ and $\hat p$ and look at the difference. I'm really confused on this.


Recall $\hat{p} = \dfrac{X}{n}$ where $X$ is a binomial random variable based on $n$ trials and success probability $p$. Then recalling that $\text{Var}(X) = np(1-p)$,

$$\text{Var}\left(\hat{p} \right) = \text{Var}\left(\dfrac{X}{n}\right) = \dfrac{1}{n^2}\text{Var}(X) = \dfrac{np(1-p)}{n^2} = \dfrac{p(1-p)}{n}$$

and since is the variance of $\hat{p}$, take the square root to obtain the standard deviation.

  • $\begingroup$ Thank you! I wasn't aware $\hat p$ was defined like that. But yeah, obviously. That is how obtained it. $\endgroup$ – Marc Dec 5 '19 at 22:20

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.