The number of individuals of species (A,B,C,D,E,F,G) at each of ten parks was counted. How would you determine which sites are most alike and which sites are most dissimilar?


Do you think this is a simple t test comparing the total number of species found at each park? Or some type of Anova comparing how many of each species was found at each park? I tried almost every ttest option and Im having a hard time meeting assumptions for the data, and JPM keeps giving me a not-normal result for the data spread as well (the data isnt normalized, and i havent found a technique to convert it into normal data)