Provides a Simple Way to Calculate ANOVAs From Fitted Linear Models.
Author marcpabst
11 Stars
Updated Last
2 Months Ago
Started In
June 2018

Analysis of Variance in Julia

Project Status: WIP – Initial development is in progress, but there has not yet been a stable, usable release suitable for the public. Build Status Coverage Status

Calculate ANOVA tables for linear models. If no anovatype argument is provided, a type III ANOVA will be calculated. Type I and II are also supported for compatibility. Support for mixed models and a more convenient way to create ANOVAs (similar to the ez package in R) is planned.

Important: Make sure to use EffectsCoding on all your predictors, or results won't be meaningful.

Minimal Example:

using RDatasets, GLM, ANOVA

data = dataset("datasets", "ToothGrowth")
categorical!(data, :Dose)

model = fit(LinearModel,
            @formula(Len ~  Supp + Dose),
            contrasts = Dict(:Supp => EffectsCoding(), :Dose => EffectsCoding()))
ANOVA table for linear model
             DF      SS     MSS       F      p
Supp        1.0  205.35  205.35 14.0166 0.0004
Dose        2.0 2426.43 1213.22 82.8109 <1e-16
Residuals  56.0 820.425 14.6504     0.0 <1e-99

Used By Packages

No packages found.