MATLAB: Minimal variance algorithm. Ideas

categorizeclusteringindexingmathematics

I don't have much experience with developing algorithms but I am considering the following problem: How to divide a set of numbers in N groups, such that the total variance is minimal? So the variance within each group is summed to get total variance.

Is it possible to calculate directly (like thresholding quantiles if I wanted groups of equal size) or does it require an iterative process?

Ive checked the code of rgb2ind but it uses some built-in functionality (cq?), and of course rgb2ind works on points in 3D space. So any help, even a reference to a handy paper or book, is welcome!

Best Answer

http://en.wikipedia.org/wiki/K-means

http://www.mathworks.com/matlabcentral/fileexchange/index?utf8=%E2%9C%93&term=k-means

Related Solutions

MATLAB: Grpstats flexibility for additional functions

If you look at the documentation the input variable whichstats can be a function handle. So for your example of the population standard deviation we can do the following:

x = rand(50,1); % Make some random data.
grpVar = logical([ones(25,1);zeros(25,1)]); % Split data into 2 groups
popStd = @(y) std(y,1); % make a function handle that computer pop. std.
myStats = grpstats(x,grpVar,popStd);

Using this method, you can make your own statistical functions. Also the list of stats given in the doc is not exhaustive. For example:

myKurt = grpstats(x,grpVar,'kurtosis');

returns the kurtosis of the groups.

MATLAB: How marginal means (also called least square means) and standard deviation are calculated from repeated measure model? I do not have any “groups” in the data, I only have 76 samples each measured in 6 locations (1 location missing in one sample)

With this model I believe the marginal means and standard deviations for the different locations are simply the raw means and standard deviations of the scores at each of the locations. The model does not seem to include anything other than location that could be adjusted for (e.g., covariates).

Best Answer

Related Solutions

MATLAB: Grpstats flexibility for additional functions

MATLAB: How marginal means (also called least square means) and standard deviation are calculated from repeated measure model? I do not have any “groups” in the data, I only have 76 samples each measured in 6 locations (1 location missing in one sample)

Related Question