0
$\begingroup$

I have blood pressure measurements for a patient over 10 time points (not equally spaced). The patient was injected with a drug after the first time point and would like to answer the question whether the drug has an effect on the patient’s blood pressure over time. Is there a statistic that can be used to answer this question? Can a simple t test be used?

Thanks

$\endgroup$
1
  • $\begingroup$ Where are we on this question? did you receive your answer ? $\endgroup$
    – Uri Goren
    Sep 12, 2015 at 8:17

1 Answer 1

0
$\begingroup$

I suggest looking in to the paired t-test before and after the drug was taken.

If you have information about delayed effect of the drug, you could use it in the test.

If not, it could also be inferred using MLE.

$\endgroup$
2
  • $\begingroup$ Thanks Uri. Since the t test assumes the independent observations, can I still use the t test given that blood pressure measurements depend on time? $\endgroup$
    – user89198
    Sep 11, 2015 at 0:47
  • $\begingroup$ I would incorporate this dependency in to the model $\endgroup$
    – Uri Goren
    Sep 11, 2015 at 16:26

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.