The Wolfram Language's symbolic architecture makes possible a uniquely convenient approach to working with statistical models. Starting from arbitrary data, the Wolfram Language generates symbolic representations of fitted models, from which a full spectrum of results and diagnostics can immediately be extracted, visualized, or used in other computations.

LinearModelFit — construct a linear regression model from data

NonlinearModelFit — construct a nonlinear regression model

GeneralizedLinearModelFit — generalized linear models, with general link functions

LogitModelFit  ▪  ProbitModelFit

model["property"] — extract properties, diagnostics, etc. from a model

model[x₁,…] — compute values of the best fit at a particular point

"BestFit"  ▪  "FitResiduals"  ▪  "ANOVATable"  ▪  "ParameterConfidenceIntervals"  ▪  "CookDistances"  ▪  "Deviances"  ▪  "AIC"  ▪  "FitCurvatureTable"  ▪  ...

FittedModel — symbolic representation of a model

Normal — extract an expression for the best fit from a symbolic model

Detailed Control

Weights  ▪  NominalVariables  ▪  LinkFunction  ▪  LinearOffsetFunction

ConfidenceLevel  ▪  VarianceEstimatorFunction  ▪  DispersionEstimatorFunction

DesignMatrix — construct a design matrix from data

Symbolic Model Discovery

FindFormula — try to find a simple symbolic formula for data

FindDistribution — try to find a simple symbolic form for the distribution of data