This is documentation for Mathematica 6, which was
based on an earlier version of the Wolfram Language.
View current documentation (Version 11.1)


performs a one-way analysis of variance.
ANOVA[data, model, vars]
performs an analysis of variance for model as a function of the categorical variables vars.
  • The data can have the form {{x_1,y_1,… ,f_1},{x_2,y_2,… ,f_2},…}, where the number of coordinates x,y,… is equal to the number of variables in the list vars.
  • For data of the form {{x1, f1}, {x2, f2}, ...} a one-way analysis of variance can be obtained without explicitly specifying the model and variable.
  • The model argument can be a list containing main effects and interactions. Main effects are elements of vars and interactions are products of main effects.
  • A full factorial model including all interactions between variables x, y, ... can be specified as {x, y, ..., All}.
  • The following options can be given:
CellMeansTruewhether cell means should be included in the output
WorkingPrecisionMachinePrecisionthe precision used in internal computations
PostTests{}significance tests to perform
SignificanceLevel0.05significance level for performed tests
A one-way analysis of variance:
Click for copyable input
A two-way analysis of variance:
Click for copyable input