I am seeking advice on how to deal with outliers when trying to calculate residual body condition indexes (by using the residuals from a regression of body mass with body length).

I am using a body condition index to explore a number of spatial ecological questions, all related to the main question of 'does body condition affect movement?'.

I need to remove/include certain individuals depending on the analysis that I am doing. So when examining some factors, it may be appropriate to include individuals which are flagged as outliers for biological relevance. Therefore, do I need to recalculate residual body condition for each test if different combinations of individuals are being used each time?

I am very new to using BCI's specifically and am not a seasoned statistician, so advice would be much appreciated!

  • $\begingroup$ Body mass is inherently a '3-D' measurement and and body length is a 1-D measurement. That might lead to "outliers" among residuals // Maybe taking logs will get rid of apparent outliers. Wouldn't guess without seeing the data. // You should be very cautious about removing "outliers" from you dataset. // Are you using length to explain mass, or both length and mass to explain something else (condition? measured how?)? $\endgroup$ – BruceET May 29 at 21:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.