How to analyze proportions from large datasets

#1
Hello all! This question will likely reveal my lack of basic statistics knowledge, but I can't seem to find the answer in textbooks or on this forum. To wit:

My grad project involves cutting fragments from leaves, and growing fungi out of them. Anywhere from 15% to 90% of fragments produce fungi, depending on the plant species the leaf came from. What I want to do is evaluate the significance of those differences between plant species. Say I have 1000 leaf fragments from species A, of which 100 grew fungi; and 700 leaf fragments from species B, of which 140 grew fungi (in total, I'll have about 15 plant species with varying numbers of leaf fragments). Each data-point is just a yes or no (0 or 1), so in the end the relevant quantity is the proportion of leaf fragments that grew fungi, for each plant species. But I can't just analyze those proportions, right? The sample size has to be incorporated somehow, to get at significance. What's the right test for this, and how do I do it?

Thank you so much for your time, and for any help you're able to offer!
 

rogojel

TS Contributor
#2
hi,
I would try a chi-squared test, with the rows being fungi yes/no and the columns the species.

I hope this helps a bit