Supported Distributions
Statistics and Machine Learning Toolbox™ supports various probability distributions, including parametric, nonparametric, continuous, and discrete distributions. The following tables list the supported probability distributions and supported ways to work with each distribution. For more information, see Working with Probability Distributions.
For a custom probability distribution, use a custom distribution template to create a
probability object and then use the Distribution Fitter app or probability object
functions. For details, see Define Custom Distributions Using the Distribution Fitter App. You can also define
a custom distribution using a function handle and use the mle
function to find maximum likelihood estimates. For an example, see
Fit Custom Distributions.
Continuous Distributions (Data)
Continuous Distributions (Statistics)
Discrete Distributions
Multivariate Distributions
Distribution | Distribution Object | Distribution-Specific Functions |
---|---|---|
Copula (Gaussian copula, t copula, Clayton copula, Frank copula, Gumbel copula) | — | copulapdf copulacdf copulaparam copulastat copulafit copularnd |
Gaussian Mixture | gmdistribution | fitgmdist pdf cdf random |
Inverse Wishart | — | iwishrnd |
Multivariate normal | — | mvnpdf mvncdf mvnrnd |
Multivariate t | — | mvtpdf mvtcdf mvtrnd |
Wishart | — | wishrnd |
Nonparametric Distributions
Distribution | Distribution Objects | Apps and Interactive UIs | Distribution-Specific Functions |
---|---|---|---|
Kernel | KernelDistribution | Distribution Fitter | ksdensity |
Pareto tails | paretotails | — | — |
Flexible Distribution Families
Distribution | Distribution-Specific Functions | Generic Functions |
---|---|---|
Pearson system | pearspdf pearscdf pearsrnd | pdf cdf random |
Johnson system | johnsrnd | — |