Korelácie

The NaN-toolbox: A statistic-toolbox for Octave and Matlab which handles data with and without MISSING VALUES encoded as NaN's.

Installing the NaN-tb with Octave:

a) You need repmat.mrepmat.m (e.g. from P.Kienzle's MATCOMPAT)

b) extract files from NaNnnn.tar.gz and move them into .../octave/.../m/statistics/base/

c) (re-)start Octave and run naninsttest. This checks whether all previous functions have been replaced

Data Set 1:

X = [4.4 5.5 4.2 3.0 4.5 4.9 4.6 5.0 4.7 5.1 4.4 4.1 4.9 4.7 5.0 4.6 3.6 4.9 5.1 4.8 5.2 5.2]';
Y = [12 14 18 35 23 29 16 12 18 21 27 13 19 22 20 16 27 21 13 18 17 11]';
scatter (x, y, [], sqrt(x.^2 + y.^2));

Data Set 2:

V = [5.8 7.3 5.6 4.0 6.0 6.5 6.2 6.6 6.3 6.8 5.8 5.5 6.5 6.3 6.6 6.1 4.8 6.5 6.8 6.4 6.9 6.9]';
T = [13 35 13 11 16 19 18 21 18 27 14 12 21 18 22 17 12 20 23 18 27 29]';
scatter (V, T, 5, sqrt(V.^2 + T.^2));
axis ([0 10 0 40]

Data Set 3:

Media:Cities.mat

scatterplotf.m

function ret=scatterplotf(x,y)
  [m,n]=size(y);
  if m==1,
    y=y';
    x=x';
  end
  dispmat=[x y];
  n=size(dispmat,2);
  dispmat=sortrows(dispmat,1);
  x=dispmat(:,1);
  y=dispmat(:,2:n);
  plot(x,y);
endfunction

Pokračovanie: PCA analýza akčných potenciálov