Hi all, I'm new to community data analysis in R and was hoping to get some feedback on my intended approach using adonis. The primary aim is to test the effect of treatment group (FOOD: F or N) on community assemblage. I have repeated measures data so I have included SITE ID as a random factor and constrained permutations to within sites (using the ?strata? argument). I want to include survey month (categorical factor) as a fixed effect in the models to look at temporal variability, and also want to include 2 other variables as random factors: vegetation and background feeding level. (Structure of data given below). Is the following appropriate? adonis(Dmatrx ~TREAT*MONTH + VEG + BKF + SITE, data=Dmetadata, strata=Dmetadata$SITE, permutations = 999) Thanks in advance, Josie 'data.frame': 413 obs. of 6 variables: $ MONTH : Factor w/ 18 levels "5","6","7","8",..: 1 1 1 1 1 1 1 1 1 1 ... $ SITE : Factor w/ 23 levels "ABER","BAYS",..: 1 9 22 19 6 14 15 4 23 18 ... $ FOOD : Factor w/ 2 levels "F","N": 2 1 1 2 2 1 2 1 1 2 ... $ VEG : Factor w/ 3 levels "1","2","3": 3 1 2 1 2 1 1 2 2 3 ... $ BKF : Factor w/ 3 levels "High","Low","Med": 3 3 3 3 1 3 3 1 1 3 ...
*Josie Galbraith* PhD student *University of Auckland * Joint Graduate School in Biodiversity and Biosecurity ? School of Biological Sciences ? Tamaki Campus ? Private Bag 92019 ? Auckland 1142* ? P:* 09-373 7599 ext. 83132 [[alternative HTML version deleted]]