mean and standard deviation of 10 fold cross validation

HOW TO PERFORM MEAN AND STANDARD DEVIATION OF TESTING ACCURACY

OF 10 FOLD CROSS VALIDATION. please help to solve this problem.Give some example for better understanding.

Answer 1

[Raghava S N]

Hi @uma,

In this example of 10-fold cross validation https://www.mathworks.com/help/bioinfo/ref/crossvalind.html#:~:text=collapse%20all-,Perform,-10%2DFold%20Cross, the testing accuracies can be recorded (which is just 1 - error rate) for each fold like this -

accuracies = zeros(10,1)
for i = 1:10
    test = (indices == i); 
    train = ~test;
    class = classify(meas(test,:),meas(train,:),species(train,:));
    classperf(cp,class,test);
    accuracies(i) = 1 - cp.ErrorRate
end

After this loop, you can find the mean and the standard deviation of the "accuracies" vector using the "mean" and "std" functions -

https://www.mathworks.com/help/matlab/ref/double.mean.html?requestedDomain=

https://www.mathworks.com/help/matlab/ref/double.std.html?searchHighlight=std&s_tid=srchtitle_support_results_1_std

Be sure to adapt this example based on your workflow and requirements.

Hope this helps!