JuliaStats

JuliaStats contains basic statistics functionality, which can be used as the foundation for statistics, machine learning, and data science needs. It is efficient, scalable, and reusable!

Installation & Setup

JuliaStats is not a single package, but rather a suite of packages. Specific packages can be downloaded depending on your needs.

To begin, import the package manager and initialize your desired package with the following code.

import Pkg
Pkg.add(*package name*)

using *package name*

For example, if you wanted to download the StatsBase package, use the following code.

import Pkg
Pkg.add("StatsBase")

using StatsBase

Commonly Used Packages

Package	Use
StatsBase.jl	Basic statistics, weights, sampling, counts, and summary statistics.
Distributions.jl	Probability distributions and related functions (PDF, CDF, sampling, etc).
StatsModel.jl	Statistical model formulas
GLM.jl	Generalized linear models (e.g., linear regression, logistic regression).
MixedModels.jl	Linear and generalized linear mixed-effects models.
HypothesisTest.jl	Statistical hypothesis tests (t-tests, chi-squared, ANOVA, etc).
MultivariateStats.jl	Multivariate analysis (PCA, factor analysis, ICA, etc).

Please refer to each package's documentation for a list of available functions and their usage.

Example

# Using StatsBase
data = ..
mean_val = mean(data)
var_val = var(data)

# Using Distributions
pdf_val = pdf(Normal(0,1), 1)

# Using GLM
df = DataFrame(..)
model = lm(@formula(y ~ x), df)

Resources

• https://github.com/JuliaStats
• https://juliastats.org/StatsModels.jl/stable/