MATLAB: Which test should I select to see if the data is normally distributed

normaldistribution kstest adtest

Hi! Help! I took some measurements on of oximetry with NIRS and I don't know which test should I use to see if my data is normally distributed. It is a continuos variable, quantitative, and I have 230 measurements. I am comparing the same measured spot under two different conditions. Is the One-sample Kolmogorov-Smirnov test the one I should use? or the two-sample? or the Anderson-Darling test? Thanks!

Best Answer

Hello, Pilar,

From what I can tell, the Distribution Fitter app is what you're looking for.

Here's a tutorial for using it: https://www.mathworks.com/help/stats/fit-a-distribution-using-the-distribution-fitting-app.html

Let me know if this helps!

Related Solutions

MATLAB: How to tell a set of data is normally distributed

normplot(x)

And for formal tests, see lillietest and jbtest

(NB: these are all Statistics Toolbox functions. If you're doing this kind of statistical work, though, I assume you have that.)

MATLAB: How to check whether the distribution of the data is a right/left skewed normal distribution using kolmogorov-smirnov test

If your data points were positive, they would look like Gamma or Chi-square distribution. Type distributionFitter in the command window and to open the distribution fitter app. There you will have options to easily fit multiple distributions and find the right one.

Best Answer

Related Solutions

MATLAB: How to tell a set of data is normally distributed

MATLAB: How to check whether the distribution of the data is a right/left skewed normal distribution using kolmogorov-smirnov test

Related Question