In my job we have a students t-test and an adjusted students t-test which is used when auto-correlation between the current and previous data is present.

Why do you have to use and adjusted t-test when auto-correlation is present? What effect does it have on dictating the statistical significance if you did hypothetically use the standard t-test?

I'd like to know this so I can fully understand the tests and explain this to others!

  • 2
    $\begingroup$ Although your question can be answered without knowing what the "adjusted Student's t-test" might be, would it be possible to tell us how it works? What kind of "autocorrelation" is involved? By disclosing these details you allow responses to focus on the kind of circumstance you are in, which might make them more relevant and understandable to you. $\endgroup$ – whuber May 18 '18 at 15:06
  • $\begingroup$ It would also help to be clear which t-test you're doing. A one-sample/paired test or an equal-variance two-sample test? While it would be possible to deal with both answers would be more straightforward if they focused on one. $\endgroup$ – Glen_b May 19 '18 at 2:30

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.