I want to test whether the skewness of the samples(from A:900*1 matrix) converge to 0 or not by using Montecarlo simulation.

Hi,

I want to test whether the skewness of the samples(from A:900*1 matrix) converge to 0 or not by using Montecarlo simulation.

In this case, what codes do I have to revise...?

load('file')

nn=100; %effective sample sizes

for n=1:1000;

~~~~~~~~~~~

ss(n)=std(r);

m(n)=mean(r);

med(n)=median(r);

nu(n)=numel(r)

skew_FP(n) = sum((r-m(n)).^3)/(length(n)-1)/ss(n).^3

end

hist(skew_FP())

xlabel('Skew_FP()')

ylabel('Frequency')

Answer 1

[Aditya]

Hello Chris,

I have reviewed your code and would like to suggest some changes to improve it:

• Before the for loop, please define the skew_FP array as follows: skew_FP = zeros(1000, 1);. This will initialize the array with zeros to store the skewness values
• To generate the r array, you can use the ‘randperm’ function. It allows you to randomly select k samples from the range of n. For example: r = randperm(n, k);
• Instead of manually calculating the skewness, you can utilize the built-in MATLAB function ‘skewness’. This function will compute the skewness of the r array directly. You can assign the result to skew_FP(n) as follows: skew_FP(n) = skewness(r);

For further details on these functions, please refer to the following documentation:

• https://in.mathworks.com/help/matlab/ref/randperm.html
• https://in.mathworks.com/help/stats/skewness.html

Hope this helps!