Beginner Question- MANOVA error in R

[SarahK]

Hi,
I have repeatedly tried to conduct a MANOVA in R but my output keeps returning "no error degrees of freedom". I have three plots each with multiple sample sites, with each sample site sampled 3 times (over 3years). I wish to compare the plots with each but also for differences in each plot over the three years. I have data which consists of just scores and data on species abundance. For this I have just been using the data which consists of just scores. I have conducted MANOVA on other datasets and it has worked fine but I can't figure out what I have done wrong here? Apologies if this is a stupid question but I am an absolute beginner and trying to figure this all out for myself!

Thanks in advance for any help!

 

[Dason]

It's not perfectly clear to me what your design is but it just sounds like you don't have enough data to fit the model you want to fit.

 

[SarahK]

Sorry, I have around 56 sites from 3 different plots each with 3 scores (2010,2011,2012). I thought I had just formatted my data incorrectly but I have tried it a number of ways to no avail. I want to see if there is significant difference between my three plots (by combining data from each sample site within the plots for each year) and I also want to see if there has been a significant change in each individual plot over the three years (which I have done a basic t-test comparing 2010-2011, 2010-2012 etc but I was unsure if this was a correct way to approach it). Thank you for your reply, hope I've made my question a bit clearer!

 

[qqplot]

Dear,

Your experiment is realy good. Do you like to compare the abundance with different factors (temperatura, salinity or between treats) again the time (years)?

 

[qqplot]

t_test just acepted two levels, tuckey is better.