avustat

Avustat is a cross-platform open-source software package designed for statistical analysis, data visualization, and educational use. It provides a modular toolkit to help researchers, students, and analysts perform data import, cleaning, exploratory analysis, modeling, and reporting in a single environment. The project emphasizes accessibility, offering a graphical user interface as well as scripting capabilities in Python and R to enable both interactive exploration and reproducible workflows.

Avustat was initiated by the Avus Foundation in 2023 to lower barriers to statistical software in higher education. After an early wave of adoption, the project released its 1.0 version in 2024 and has since seen ongoing community-driven development, with regular updates and expanding ecosystem support, including Jupyter integration and web dashboards.

Key features include data import from CSV, Excel, and SQL databases; robust data cleaning and transformation; descriptive statistics, hypothesis testing (t-tests, ANOVA, chi-square tests), regression and generalized linear models, time-series analysis, and Bayesian methods. Visualization supports histograms, scatter plots, boxplots, QQ plots, and interactive dashboards. Reports can be generated as notebooks, PDFs, or HTML dashboards, and projects are designed for reproducibility through configuration files and version control-friendly workflows.

Architecturally, Avustat combines a performance-oriented core implemented in Rust with high-level interfaces in Python and R. It employs a plugin architecture enabling third-party extensions and adapters for various data sources. Data storage leverages an embedded SQLite database for project state, while data access is mediated by a modular adapter layer to external sources.

Avustat is released under the MIT License and maintains an active community of contributors from universities and independent developers. It is widely used in education and research settings for its approachable design and integrated workflow, though users sometimes note that very large datasets may require additional optimization or external tooling. See also statistical software ecosystems such as R, SciPy/statsmodels in Python, and Julia’s StatsKit.