1
$\begingroup$

I'm wondering how to combine the SDs for two results. I have the standard deviations of the baseline results and the SDs of the change from baseline. I'm wondering how to calculate the SD of the endpoint.

How do I do this?

$\endgroup$
1
$\begingroup$

There is a simple formula for the variance which is just the square of the standard deviatiotn. $$\text{Var}(X + Y) = \text{Var}(X) + \text{Var}(Y) + 2\text{Cov}(X, Y)$$

In your case $X$ is the baseline result and $Y$ is the change. The critical thing is that you also need the covariance, which you did not mention.

Just as an additional remark, it is unlikely that the covariance is zero. For example, if your values are scores on some test and the change comes from a special intervention, people with a low baseline often profit more.

$\endgroup$

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.