0
$\begingroup$

I have data. Soil samples were taken from meadows and adjacent arable fields (see picture):

sampling pattern

There are always three samples per each opposing site. Since those 6 spatially conjoined sampling points are supposedly related, I need a nested design.

Now, I want to do a t-test. I.e., I would like to compare all samples beneath meadows and arable fields where the subgroups are the 3 conjoined points for each type of vegetation.

Since I cannot find a way I comprehend in the internet literature, can someone help me out here?

$\endgroup$
0
$\begingroup$

There is no "nested t-test". A t-test compares two means (or sometimes one mean to a constant).

You actually have quite a complex design. I think you should hire a consultant.

$\endgroup$
  • $\begingroup$ Thank you! Why cannot be there a t test? I still have values to compare just differently weightd? I'm not a statistican. But is there an explanation? Thank you! $\endgroup$ – Vera Maria Nov 28 '18 at 13:26

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.