Documentation of corr_nan3

Global Index (short | long) | Local contents | Local Index (short | long)

Function Synopsis

c = covar_nan(mat1, mat2, tol, show);

Help text

  function c = covar_nan ( mat1 , mat2 , tol , show ) ;

  This function computes the covariance matrix between
  mat1 and mat2, which may contain NaNs.  Elements of
  either matrix that have NaNs are ignored.

  It is assumed that the covariance will be taken along 
  the column dimension of mat1 and mat2.

  show = 'show', 'noshow', or 1, 0, respectively.

Cross-Reference Information

Listing of function corr_nan3

function c = covar_nan(mat1, mat2, tol, show);

if nargin < 3; tol = 2; end;

if nargin < 4; show = 0; end;
if isstr(show);
  show = strcmp(show, 'show');
end

if (size(mat1, 1) ~= size(mat2, 1));
  error('The number of columns of mat1 and mat2 must be equal');
end

[m1, n1] = size(mat1);
[m2, n2] = size(mat2);

if show; disp(['Number of iterations:  ' num2str(n1)]); end;

c = repmat(NaN, [n1, n2]);
for i = 1:n1; 
  if show; 
    disp(['Iteration ' num2str(i) ' of ' num2str(n1)]); 
  end;
  for j = 1:n2;
    kp = find(~isnan(mat1(:,i).*mat2(:,j))); nkp = length(kp);
    if nkp > tol;
      c(i,j) = standardize(mat1(kp,i))'*standardize(mat2(kp,j))/(nkp-1);
    end
  end
end