Help deciding stats for project

#1
Hi,
I'm fairly new to stats but I could really do with some help to decide which stats test would be best to use for my project. I have access to R and SPSS.

I’m investigating whether there is a correlation between ground flora diversity and invertebrate diversity in woodland and will have about 20 quadrants and may only be able to take up to 6 measurements from each over the summer.

I will also be collecting data on soil (pH, composition), light intensity and other bits and pieces so ideally I need to incorporate that data too.

Many thanks,
Julie
 

Karabiner

TS Contributor
#2
So you have n=20 quadrants to study, and you will have longitudinal data, since flora diversity, invertebrate diversity, pH, composition, light intenity etc. will be measured at 6 different time points in each of the 20 quadrants?

With kind regards

Karabiner
 
#3
Thank you, yes that makes sense. How would I go about analysing that? Is there a better method or/and program to do that? Sorry I have no idea what I'm doing at the moment.
Many thanks
 

Karabiner

TS Contributor
#4
Since there is a clustering of data (data from 6 time points within each participant), I suppose
that multilevel modeling (multilevel regression) would make the most use of it. This not easy
to do for someone who is new to statistics. Is there someone available in real life who you can
consult on such matters?

With kind regards

Karabiner
 
#5
Yes, I can get help from uni to actually do the stats, I just needed to figure out what stats I need to use for my project proposal.
Thank you for your help, and pointing me in the right direction.