Given a data set (.mat file). How can I identify the distribution (Normal, Gaussian, etc) of the data in matlab? Is there any built-in function that helps to do this?
For example, I'd like to identify the distribution of the Ionosphere data set.
The kstest is a MATLAB function that can be used for this purpose. It is based on the kolmogorov-Smirnov test and gives you the option to test different distributions with different significance level for your data.
I suppose the simplest way would be to load the dataset and plot histograms for each feature value of the dataset.
The UCI Ionosphere dataset consists of 34 feature attributes out of which some seem normally distributed (Gaussian) and the others look a lot like Poisson distribution. I've attached the overlapped histograms over all features. It would be better though to visualize them separately.
also u can use fitdist(data, 'poisson') function to fit the distribution of a dataset.
- Badges
- Science topic