Help!

#1
I have a problem that is probably fairly simple but I have writers block.
This is to do with unnamed animals. I have three tests I have conducted on different samples of animals. The possible outputs are simply alive/dead (please ignore the obvious moral implications). The tests are: Small change in habitat(small), and large change in habitat (large) and no change in habitat (None).
This is the ultimate output
..............small.......large.....none
Alive.........47...........39.........45
Dead .........1...........12.........5

How can I tell if the treatments had any statistical difference (two way Anova?) Could somebody please help?
 

hlsmith

Less is more. Stay pure. Stay poor.
#2
Did you randomize animals to treatments?


You are likely looking at a Fishers Exact Test. If significant you can follow it up with pairwise comparisons of groups using Fisher's exact test again. Also, look up the topic of false discovery rate.