Distribution fitting

Distribution fitting is the fitting of a probability distribution to a series of data to predict the probability of variable phenomena in a certain interval. We can get good predictions from the distribution, which is a close fit to the data. Depending on the characteristics of the distribution and of the phenomenon, some can be fitted more closely with the data:

julia> d = fit(Distribution_type, dataset) 

This fits a distribution of type Distribution_type to a given dataset; dataset.x is of the array type and comprises all the samples. The fit function finds the best way to fit the distribution.

Distribution selection

The distribution is selected by the symmetry or the skewness of the data with respect to the mean value.

Symmetrical distributions

For symmetrical distributions tending to have the bell curve, the normal distribution and the logistic distributions are most suited. When the kurtosis is higher, the values are spread far away from the center, and then...