Skip to main content
Cross Validated

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

4
  • $\begingroup$ Thanks the challenge is that I only have the summary statistics mean, SE and sample size, so do not know the co-variance between A and B. $\endgroup$ Commented Apr 28 at 10:06
  • 1
    $\begingroup$ But, A and B will be correlated. $\endgroup$ Commented Apr 28 at 10:09
  • 2
    $\begingroup$ You'll have a hard time doing anything if there is correlation, but you have no idea what it is (I guess you can plot the SE of A/B for all possible values). You might have to guess or elicit from experts or estimate from other data or something else... $\endgroup$ Commented 2 days ago
  • 1
    $\begingroup$ Fieller's Theorem is also an option - when you know the correlation. As @Björn implies, without knowledge of the correlation between A and B, you are on very shaky ground because, whilst the equations will still "work", your conclusions will be unreliable. $\endgroup$ Commented 2 days ago