Abundance estimates: Testing for (significant) differences

Forum for discussion of general questions related to study design and/or analysis of existing data - software neutral.

Abundance estimates: Testing for (significant) differences

Postby Tana » Thu Jul 09, 2020 4:37 pm

Hi everyone,

I have a question regarding the comparison of abundance estimates obtained with different methods.

I have a CMR abundance estimate and Independent Double Observer estimate (corrected for availability) and would like to test if the two estimates differ significantly. (Both estimates were obtained on the same population at the same time. 95%-CIs do not overlap, but are quite close together). In most of the papers I have read so far about method comparison, I haven’t seen any statistical test for estimate comparison. But in one or the other paper I saw that abundance estimates were compared with a z-test, with (Estimate1-Estimate2) / sqrt(SE1^2+SE2^2).

So, my question now is: Is it “valid” to use the z-test to test for significance in abundance estimates of different methods, and can I use that to compare a CMR estimate with that of another method?

Any hint (reference to papers etc.) would be appreciated.
Thanks a lot.
Tana
 
Posts: 3
Joined: Mon Jun 15, 2020 3:23 pm

Return to analysis & design questions

Who is online

Users browsing this forum: No registered users and 18 guests