My knowledge of statistics is limited and I am looking for resources to read on the matter if possible.

Anyways, I am currently trying to estimate a confidence interval for a proportion over time. The specific example pertains to a trader's Win % as he make more trades. My current idea is to take the first $n$ sample data to calculate a proportion, then see how that changes over the amount of trades. I want to ultimately calculate the variability of the win %. My confidence interval would be calculated as such:

$$p \pm \sqrt[2]{\frac{1}{n} * p(1-p)}$$

I know this is clearly the wrong approach to look into but I would appreciate it if I am pointed to in the right direction.

  • 1
    $\begingroup$ I wouldn't be so quick to dismiss this approach as "clearly ... wrong," especially if $np$ and $n(1-p)$ will both be large. It has a theoretical foundation, is easy to compute and interpret, may provide a meaningful envelope around the observed percentage (especially if the square root is multiplied by a suitable constant), and could function well to enhance visual or exploratory examination of the data. One avenue to pursue would be quality-control procedures for count data. $\endgroup$
    – whuber
    Jun 23, 2014 at 20:22
  • $\begingroup$ I will more than likely use a Z-score of 80% confidence. Thanks for the link, I will look into it. $\endgroup$
    – Kevin Pei
    Jun 23, 2014 at 20:34
  • $\begingroup$ An alternative would be to start with logistic regression, and then see if the residuals are correlated in time. $\endgroup$ Jan 27, 2017 at 10:35


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.