How to find the coefficient of determination (R2) between 2 variables in netcdf?
2 views (last 30 days)
Show older comments
I have attached a zipped netcdf file ('ssh.nc').
I wanted to do a corellation test (OR to find the R2 value between two variables). The two variables are 'zos' and 'bottomT' which have the following dimensions of longitude,latitude,time. After this I wanted to plot a map so I can find out in which regions the correlation is high/low.
I tried to use ncread and extract grid-by-grid values but it is time- consuming and I might be prone to making errors. Is there any code that can find the correlation between two variables?
Would be grateful for assistance in this.
0 Comments
Answers (1)
KSSV
on 4 Dec 2018
It depends whether you want to find it spatially or temporally. I feel temporal regression is the one you are looking for. Check this code:
ncfile = 'ssh.nc' ;
A = ncread(ncfile,'zos') ;
B = ncread(ncfile,'bottomT') ;
[nx,ny,nt] = size(A) ;
R = zeros(nx,ny) ;
for i = 1:nx
for j = 1:ny
Ai = squeeze(A(i,j,:)) ;
Bi = squeeze(B(i,j,:)) ;
R(i,j) = regression(Ai',Bi')^2 ;
end
end
See Also
Categories
Find more on NetCDF in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!