Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

What are good ways of describe observed tick data latency with a view to flagging when something is systematically wrong?

For example, we would want to discount outlier ticks so that we do not alert on one tick in a thousand that has high latency, but do want to capture sustained increased beyond acceptable thresholds.

Would an expoential moving average over N ticks or a period T be appropriate?

share|improve this question
    
Your second paragraph doesn't make sense to me. What does it mean "we do not alert on one tick in a thousand that has high latency". What is this so-called "alerting"? I also don't understand "sustained increased beyond acceptable thresholds". What exactly is increasing and what threshold are we talking about? – user2763361 Feb 3 '14 at 16:09

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.